Recent zbMATH articles in MSC 62https://zbmath.org/atom/cc/622024-03-13T18:33:02.981707ZUnknown authorWerkzeugLadislaus von Bortkiewicz -- statistician, economist and a European intellectualhttps://zbmath.org/1528.010102024-03-13T18:33:02.981707Z"Härdle, Wolfgang Karl"https://zbmath.org/authors/?q=ai:hardle.wolfgang-karl"Vogt, Annette B."https://zbmath.org/authors/?q=ai:vogt.annette-bThe paper is devoted to a presentation of the life and work of Ladislaus von Bortkiewicz (1868--1931). He was a European statistician and worked scientifically in theoretical economics, stochastics, mathematical statistics and radiology. It is stressed that his clear views on mathematical principles with their applications in these fields were in conflict with the mainstream economic schools in Germany at the dawn of the 20th century. His prominent role in today's statistical thinking is pointed out.
Reviewer: Roman Murawski (Poznań)The three faces of faithfulnesshttps://zbmath.org/1528.031412024-03-13T18:33:02.981707Z"Zhang, Jiji"https://zbmath.org/authors/?q=ai:zhang.jiji"Spirtes, Peter"https://zbmath.org/authors/?q=ai:spirtes.peterSummary: In the causal inference framework of Spirtes, Glymour, and Scheines (SGS) [\textit{P. Spirtes} et al., Causation, prediction, and search. With additional material by David Heckerman, Christopher Meek, Gregory F. Cooper and Thomas Richardson. 2nd ed. Cambridge, MA: MIT Press (2001; Zbl 0981.62001)], inferences about causal relationships are made from samples from probability distributions and a number of assumptions relating causal relations to probability distributions. The most controversial of these assumptions is the Causal Faithfulness Assumption, which roughly states that if a conditional independence statement is true of a probability distribution generated by a causal structure, it is entailed by the causal structure and not just for particular parameter values. In this paper we show that the addition of the Causal Faithfulness Assumption plays three quite different roles in the SGS framework: (i) it reduces the degree of underdetermination of causal structure by probability distribution; (ii) computationally, it justifies reliable (constraint-based) causal inference algorithms that would otherwise have to be slower in order to be reliable; and (iii) statistically, it implies that those algorithms reliably obtain the correct answer at smaller sample sizes than would otherwise be the case. We also consider a number of variations on the Causal Faithfulness Assumption, and show how they affect each of these three roles.Optimal aquaculture planning while accounting for the size spectrumhttps://zbmath.org/1528.370792024-03-13T18:33:02.981707Z"Yoshioka, Hidekazu"https://zbmath.org/authors/?q=ai:yoshioka.hidekazuSummary: Aquaculture planning of a fish species requires a balance between the feeding costs and commercial benefits while considering that the resources should not be disposed of at the terminal time. Furthermore, the planning process should account for the size spectrum, namely that different individual fishes have different body sizes. Herein, we present a novel dynamic programming method to anticipate and tackle these issues consistently. The opening time of harvesting and the subsequent harvesting policy after that time are the decision variables. The novelty of the presented model is its ability to efficiently describe the distributed body weights based on a logistic growth model having an unknown maximum body weight distributed according to a probability measure. We start from a discrete-time and discrete-state model on a daily basis and then obtain its continuous-state counterpart. The innovative two models are presented for the first time, and the former serves as the fully implementable numerical discretization of the latter. We present application examples of the proposed models to real data of an ongoing aquaculture system for the ayu sweetfish \textit{Plecoglossus altivelis altivelis} in Japan.Approximation bounds for norm constrained neural networks with applications to regression and GANshttps://zbmath.org/1528.410352024-03-13T18:33:02.981707Z"Jiao, Yuling"https://zbmath.org/authors/?q=ai:jiao.yuling"Wang, Yang"https://zbmath.org/authors/?q=ai:wang.yang.1"Yang, Yunfei"https://zbmath.org/authors/?q=ai:yang.yunfeiSummary: This paper studies the approximation capacity of ReLU neural networks with norm constraint on the weights. We prove upper and lower bounds on the approximation error of these networks for smooth function classes. The lower bound is derived through the Rademacher complexity of neural networks, which may be of independent interest. We apply these approximation bounds to analyze the convergences of regression using norm constrained neural networks and distribution estimation by GANs. In particular, we obtain convergence rates for over-parameterized neural networks. It is also shown that GANs can achieve optimal rate of learning probability distributions, when the discriminator is a properly chosen norm constrained neural network.Frame-type kernel and time-frequency transformshttps://zbmath.org/1528.420112024-03-13T18:33:02.981707Z"Chen, Qiuhui"https://zbmath.org/authors/?q=ai:chen.qiuhui"Zhang, Yiqiao"https://zbmath.org/authors/?q=ai:zhang.yiqiao(no abstract)An extension of Aitken's integral for Gaussians and positive definitenesshttps://zbmath.org/1528.420152024-03-13T18:33:02.981707Z"Menegatto, V. A."https://zbmath.org/authors/?q=ai:menegatto.valdir-antonio"Oliveira, C. P."https://zbmath.org/authors/?q=ai:oliveira.claudemir-pIn this paper, the authors provide conditions for the kernels below to be positive definite and strictly positive definite on an arbitrary set \(Y\):
(1) \(K_m:Y\times Y\to \mathbb R\) defined by
\[
K_m(y,y^\prime)=\frac1{[\det G(y,y^\prime)]^{m/2}}, \quad \text{or}\quad K_m(y,y^\prime)=\frac{\phi(H(y,y')^\top G(y,y^\prime)^{-1}H(y,y^\prime))}{[\det G(y,y^\prime)]^{m/2}};
\]
(2) \(K_m:Y\times Y\to \mathbb C\) defined by
\[
K_m(y,y^\prime)=\frac1{[\det G(y,y^\prime)]^{m/2}}\int_0^\infty{\phi(H(y,y^\prime)^\top G(y,y^\prime)^{-1}H(y,y^\prime)s)P_s(y,y^\prime)}ds,
\]
where \(G:Y\times Y\to M_q(\mathbb R)\) is a conditionally negative definite matrix-valued function, \(H:Y\times Y\to\mathbb R^q\) is an exponentially positive definite vector function, \(\phi:(0,\infty)\to\mathbb R\) is a bounded and completely monotone function and \(P_s:Y\times Y\to\mathbb R\) are positive definite functions. Using these results, models involving the negative power function, the Cauchy function, the parabolic cylinder function, and the Matérn function are presented.
Finally, conditions for positive definiteness on a product \(X\times Y\), where \(X\) is also an arbitrary set, of the real-valued kernel
\[
K_m((x,y),(x^\prime y^\prime))=\frac{\phi(H(x,x^\prime)^\top G(y,y^\prime))^{-1}H(x,x^\prime)}{[\det G(y,y^\prime)]^{m/2}}, \quad x,x^\prime\in X,y,y^\prime \in Y,
\]
are provided.
Reviewer: Ana Paula Peron (São Carlos)Geometric science of information. 6th international conference, GSI 2023, St. Malo, France, August 30 -- September 1, 2023. Proceedings. Part IIhttps://zbmath.org/1528.530022024-03-13T18:33:02.981707ZThe articles of this volume will be reviewed individually. For the preceding conference see [Zbl 1482.94007]. For Part II of the proceedings of the present conference see [Zbl 1528.94003].
Indexed articles:
\textit{Terze, Zdravko; Zlatar, Dario; Kasalo, Marko; Andrić, Marijan}, Lie group quaternion attitude-reconstruction of quadrotor UAV, 3-11 [Zbl 07789278]
\textit{de Saxcé, Géry}, A variational principle of minimum for Navier-Stokes equation based on the symplectic formalism, 12-21 [Zbl 07789279]
\textit{Dubois, François; Rojas-Quintero, Juan Antonio}, A variational symplectic scheme based on Simpson's quadrature, 22-31 [Zbl 07789280]
\textit{Bergshoeff, Eric}, Generalized Galilean geometries, 32-40 [Zbl 07789281]
\textit{Crespo, Mewen; Casale, Guy; Le Marrec, Loïc}, Continuum mechanics of defective media: an approach using fiber bundles, 41-49 [Zbl 07789282]
\textit{Coquinot, Baptiste; Mir, Pau; Miranda, Eva}, Singular cotangent models in fluids with dissipation, 50-59 [Zbl 07789283]
\textit{Li, Tianzhi; Wang, Jinzhi}, Multisymplectic unscented Kalman filter for geometrically exact beams, 60-68 [Zbl 07789284]
\textit{Cardall, Christian Y.}, Towards full `Galilei general relativity': Bargmann-Minkowski and Bargmann-Galilei spacetimes, 69-78 [Zbl 07789285]
\textit{Colombo, Leonardo; Goodman, Jacob}, Existence of global minimizer for elastic variational obstacle avoidance problems on Riemannian manifolds, 81-88 [Zbl 07789286]
\textit{Stratoglou, Efstratios; Anahory Simoes, Alexandre; Bloch, Anthony; Colombo, Leonardo}, Virtual affine nonholonomic constraints, 89-96 [Zbl 07789287]
\textit{Simoes, Alexandre Anahory; Colombo, Leonardo}, Nonholonomic systems with inequality constraints, 97-104 [Zbl 07789288]
\textit{de León, Manuel; Lainz, Manuel; López-Gordón, Asier; Marrero, Juan Carlos}, Nonholonomic brackets: Eden revisited, 105-112 [Zbl 07789289]
\textit{Cushman, Richard}, The momentum mapping of the affine real symplectic group, 115-123 [Zbl 07789290]
\textit{El Morsalani, Mohamed}, Polysymplectic Souriau Lie group thermodynamics and the geometric structure of its coadjoint orbits, 124-133 [Zbl 07789291]
\textit{El Morsalani, Mohamed}, Polysymplectic Souriau Lie group thermodynamics and entropy geometric structure as Casimir invariant function, 134-143 [Zbl 07789292]
\textit{Bieliavsky, Pierre; Dendoncker, Valentin; Neuttiens, Guillaume; Pierard de Maujouy, Jérémie}, Riemannian geometry of Gibbs cones associated to nilpotent orbits of simple Lie groups, 144-151 [Zbl 07789293]
\textit{Barbaresco, Frédéric}, Symplectic foliation transverse structure and Libermann foliation of heat theory and information geometry, 152-164 [Zbl 07789294]
\textit{Combe, Noemie; Combe, Philippe; Nencka, Hanna}, Poisson geometry of the statistical Frobenius manifold, 165-172 [Zbl 07789295]
\textit{Boyom, Michel Nguiffo}, Canonical Hamiltonian systems in symplectic statistical manifolds, 173-180 [Zbl 07789296]
\textit{Naudts, Jan}, A dually flat geometry for spacetime in 5d, 183-191 [Zbl 07789297]
\textit{Bendimerad-Hohl, Antoine; Haine, Ghislain; Matignon, Denis}, Structure-preserving discretization of the Cahn-Hilliard equations recast as a port-Hamiltonian system, 192-201 [Zbl 07789298]
\textit{Rodríguez Abella, Álvaro; Gay-Balmaz, François; Yoshimura, Hiroaki}, Infinite dimensional Lagrange-Dirac mechanics with boundary conditions, 202-211 [Zbl 07789299]
\textit{Wu, Meng; Gay-Balmaz, François}, Variational integrators for stochastic Hamiltonian systems on Lie groups, 212-220 [Zbl 07789300]
\textit{Yoshimura, Hiroaki; Gay-Balmaz, François}, Hamiltonian variational formulation for non-simple thermodynamic systems, 221-230 [Zbl 07789301]
\textit{Bergold, Paul; Tronci, Cesare}, Madelung transform and variational asymptotics in Born-Oppenheimer molecular dynamics, 231-241 [Zbl 07789302]
\textit{Castrillón López, Marco}, Conservation laws as part of Lagrangian reduction. Application to image evolution, 242-250 [Zbl 07789303]
\textit{Bauer, Werner; Brecht, Rüdiger}, Casimir-dissipation stabilized stochastic rotating shallow water equations on the sphere, 253-262 [Zbl 07789304]
\textit{Possanner, Stefan; Holderied, Florian; Li, Yingzhe; Na, Byung Kyu; Bell, Dominik; Hadjout, Said; Güçlü, Yaman}, High-order structure-preserving algorithms for plasma hybrid models, 263-271 [Zbl 07789305]
\textit{Spera, Mauro}, Hydrodynamics of the probability current in Schrödinger theory, 272-281 [Zbl 07789306]
\textit{Gay-Balmaz, François; Wu, Meng; Eldred, Chris}, Variational geometric description for fluids with permeable boundaries, 282-289 [Zbl 07789307]
\textit{Tronci, Cesare; Gay-Balmaz, François}, Lagrangian trajectories and closure models in mixed quantum-classical dynamics, 290-300 [Zbl 07789308]
\textit{Vizman, Cornelia}, A discrete version for vortex loops in 2D fluids, 301-309 [Zbl 07789309]
\textit{Ortega, Juan-Pablo; Yin, Daiying}, Expressiveness and structure preservation in learning port-Hamiltonian systems, 313-322 [Zbl 07789310]
\textit{Chrétien, Stéphane; Vaucher, Rémi}, Signature estimation and signal recovery using median of means, 323-331 [Zbl 07789311]
\textit{Toshev, Artur P.; Galletti, Gianluca; Brandstetter, Johannes; Adami, Stefan; Adams, Nikolaus A.}, Learning Lagrangian fluid mechanics with E(3)-equivariant graph neural networks, 332-341 [Zbl 07789312]
\textit{Jiang, Haotian; Li, Qianxiao}, Forward and inverse approximation theory for linear temporal convolutional networks, 342-350 [Zbl 07789313]
\textit{Nakamura, Takemi}, Monotonicity of the scalar curvature of the quantum exponential family for transverse-field Ising chains, 353-362 [Zbl 07789314]
\textit{Ciaglia, F. M.; Di Cosmo, F.; González-Bravo, L.}, Can Čencov meet Petz, 363-371 [Zbl 07789315]
\textit{Barbaresco, Frederic}, Souriau's geometric principles for quantum mechanics, 372-381 [Zbl 07789316]
\textit{Jacquet, Philippe; Joly, Véronique}, Unitarity excess in Schwartzschild metric, 382-391 [Zbl 07789317]
\textit{Verrier, Gabriel; Haine, Ghislain; Matignon, Denis}, Modelling and structure-preserving discretization of the Schrödinger as a port-Hamiltonian system, and simulation of a controlled quantum box, 392-401 [Zbl 07789318]
\textit{Ciaglia, Florio M.; Di Cosmo, Fabio}, Some remarks on the notion of transition, 402-411 [Zbl 07789319]
\textit{de Gosson, Maurice A.}, Geometric quantum states and Lagrangian polar duality: quantum mechanics without wavefunctions, 412-419 [Zbl 07789320]
\textit{Mama Assandje, Prosper Rosaire; Dongho, Joseph; Bouetou, Thomas Bouetou}, Complete integrability of gradient systems on a manifold admitting a potential in odd dimension, 423-432 [Zbl 07789321]
\textit{Drumetz, Lucas; Reiffers-Masson, Alexandre; El Bekri, Naoufal; Vermet, Franck}, Geometry-preserving Lie group integrators for differential equations on the manifold of symmetric positive definite matrices, 433-443 [Zbl 07789322]
\textit{Uwano, Yoshio}, The phase space description of the geodesics on the statistical model on a finite set. Trajectory-confinement and integrability, 444-453 [Zbl 07789323]
\textit{Tarama, Daisuke; Françoise, Jean-Pierre}, Geodesic flows of \(\alpha \)-connections for statistical transformation models on a compact Lie group, 454-462 [Zbl 07789324]
\textit{Galeotti, Mattia; Citti, Giovanna; Sarti, Alessandro}, Differential operators heterogenous in orientation and scale in the \(V_1\) cortex, 465-473 [Zbl 07789325]
\textit{Liontou, Vasiliki}, Gabor frames and contact structures: signal encoding and decoding in the primary visual cortex, 474-482 [Zbl 07789326]
\textit{Mazzetti, Caterina; Sarti, Alessandro; Citti, Giovanna}, A sub-Riemannian model of the functional architecture of M1 for arm movement direction, 483-492 [Zbl 07789327]
\textit{Alekseevsky, D. V.; Shirokov, I. M.}, Geometry of saccades and saccadic cycles, 493-500 [Zbl 07789328]
\textit{Tamekue, Cyprien; Prandi, Dario; Chitour, Yacine}, MacKay-type visual illusions via neural fields, 501-508 [Zbl 07789329]
\textit{Da Rocha, Wagner; Lavor, Carlile; Liberti, Leo; Malliavin, Thérèse E.}, Pseudo-dihedral angles in proteins providing a new description of the Ramachandran map, 511-519 [Zbl 07789330]
\textit{Hengeveld, Simon B.; Merabti, Mathieu; Pascale, Fabien; Malliavin, Thérèse E.}, A study on the covalent geometry of proteins and its impact on distance geometry, 520-530 [Zbl 07789331]
\textit{Huang, Shu-Yu; Chang, Chi-Fon; Lin, Jung-Hsin; Malliavin, Thérèse E.}, Exploration of conformations for an intrinsically disordered protein, 531-540 [Zbl 07789332]
\textit{Tumpach, Alice Barbora; Kán, Peter}, Temporal alignment of human motion data: a geometric point of view, 541-550 [Zbl 07789333]
\textit{Hengeveld, S. B.; Plastria, F.; Mucherino, A.; Pelta, D. A.}, A linear program for points of interest relocation in adaptive maps, 551-559 [Zbl 07789334]
\textit{Wohrer, Adrien}, Diffeomorphic ICP registration for single and multiple point sets, 563-573 [Zbl 07789335]
\textit{Makaroff, Nicolas; Cohen, Laurent D.}, Chan-Vese attention U-net: an attention mechanism for robust segmentation, 574-582 [Zbl 07789336]
\textit{Li, Wanxin; Prasad, Ashok; Miolane, Nina; Dao Duc, Khanh}, Using a Riemannian elastic metric for statistical analysis of tumor cell shape heterogeneity, 583-592 [Zbl 07789337]
\textit{Lefevre, Julien; Fraize, Justine; Germanaud, David}, Perturbation of Fiedler vector: interest for graph measures and shape analysis, 593-601 [Zbl 07789338]
\textit{Kratsios, Anastasis; Hyndman, Cody}, Generative OrnsteinUhlenbeck markets via geometric deep learning, 605-614 [Zbl 07789339]
\textit{Lagrave, Pierre-Yves}, \(\mathrm{SL}(2,\mathbb{Z})\)-equivariant machine learning with modular forms theory and applications, 615-623 [Zbl 07789340]
\textit{Camarinha, Margarida; Machado, Luís; Silva Leite, Fátima}, K-splines on SPD manifolds, 624-633 [Zbl 07789341]
\textit{Lapenna, M.; Faglioni, F.; Zanchetta, F.; Fioresi, R.}, Geometric deep learning: a temperature based analysis of graph neural networks, 634-643 [Zbl 07789342]A conversation with Paul Embrechtshttps://zbmath.org/1528.600032024-03-13T18:33:02.981707Z"Genest, Christian"https://zbmath.org/authors/?q=ai:genest.christian"Nešlehová, Johanna G."https://zbmath.org/authors/?q=ai:neslehova.johanna-gSummary: Paul Embrechts was born in Schoten, Belgium, on 3 February 1953. He holds a Licentiaat in Mathematics from Universiteit Antwerpen (1975) and a DSc from Katholieke Universiteit Leuven (1979), where he was also a Research Assistant from 1975 to 1983. He then held a lectureship in Statistics at Imperial College, London (1983-1985) and was a Docent at Limburgs Universitair Centrum, Belgium (1985-1989) before joining ETH Zürich as a Full Professor of Mathematics in 1989, where he remained until his retirement as an Emeritus in 2018. A renowned specialist of extreme-value theory and quantitative risk management, he authored or coauthored nearly 200 scientific papers and five books, including the highly influential `Modelling of Extremal Events for Insurance and Finance' (Springer, 1997) and `Quantitative Risk Management: Concepts, Techniques and Tools' (Princeton University Press, 2005, 2015). He served in numerous editorial capacities, notably as Editor-in-Chief of the (1996-2005). Praised for his natural leadership and exceptional communication skills, he helped to bridge the gap between academia and industry through the foundation of RiskLab Switzerland and his sustained leadership for nearly 20 years. He gave numerous prestigious invited and keynote lectures worldwide and served as a member of the board of, or consultant for, various banks, insurance companies and international regulatory authorities. His work was recognised through several visiting positions, including at the Oxford-Man Institute, and many awards. He is, inter alia, an Elected Fellow of the Institute of Mathematical Statistics (1995) and the American Statistical Association (2014), an Honorary Fellow of the Institute and the Faculty of Actuaries (2000), Honorary Member of the Belgian (2010) and French (2015) Institute of Actuaries and was granted four honorary degrees (University of Waterloo, 2007; Heriot-Watt University, 2011; Université catholique de Louvain, 2012; City, University of London, 2017). The following conversation took place in Paul's office at ETH Zürich, 17-18 December 2018.
{{\copyright} 2020 The Authors. International Statistical Review published by John Wiley \& Sons Ltd on behalf of International Statistical Institute.}The basic distributional theory for the product of zero mean correlated normal random variableshttps://zbmath.org/1528.600172024-03-13T18:33:02.981707Z"Gaunt, Robert E."https://zbmath.org/authors/?q=ai:gaunt.robert-edwardSummary: The product of two zero mean correlated normal random variables, and more generally the sum of independent copies of such random variables, has received much attention in the statistics literature and appears in many application areas. However, many important distributional properties are yet to be recorded. This review paper fills this gap by providing the basic distributional theory for the sum of independent copies of the product of two zero mean correlated normal random variables. Properties covered include probability and cumulative distribution functions, generating functions, moments and cumulants, mode and median, Stein characterisations, representations in terms of other random variables, and a list of related distributions. We also review how the product of two zero mean correlated normal random variables arises naturally as a limiting distribution, with an example given for the distributional approximation of double Wiener-Itô integrals.
{{\copyright} 2022 The Author. \textit{Statistica Neerlandica} published by John Wiley \& Sons Ltd on behalf of Netherlands Society for Statistics and Operations Research.}On quantile-based asymmetric family of distributions: properties and inferencehttps://zbmath.org/1528.600182024-03-13T18:33:02.981707Z"Gijbels, Irène"https://zbmath.org/authors/?q=ai:gijbels.irene"Karim, Rezaul"https://zbmath.org/authors/?q=ai:karim.rezaul"Verhasselt, Anneleen"https://zbmath.org/authors/?q=ai:verhasselt.anneleenSummary: In this paper, we provide a detailed study of a general family of asymmetric densities. In the general framework, we establish expressions for important characteristics of the distributions and discuss estimation of the parameters via method-of-moments as well as maximum likelihood estimation. Asymptotic normality results for the estimators are provided. The results under the general framework are then applied to some specific examples of asymmetric densities. The use of the asymmetric densities is illustrated in a real-data analysis.
{{\copyright} 2019 The Authors. International Statistical Review {\copyright} 2019 International Statistical Institute}Response to the letter to the editor on ``On quantile-based asymmetric family of distributions: properties and inference''https://zbmath.org/1528.600192024-03-13T18:33:02.981707Z"Gijbels, Irène"https://zbmath.org/authors/?q=ai:gijbels.irene"Karim, Rezaul"https://zbmath.org/authors/?q=ai:karim.rezaul"Verhasselt, Anneleen"https://zbmath.org/authors/?q=ai:verhasselt.anneleenSummary: \textit{F. J. R. Alvarez} [Int. Stat. Rev. 88, No. 3, 793--796 (2020; Zbl 1528.60021)] points out an identification problem for the four-parameter family of two-piece asymmetric densities introduced by \textit{V. Nassiri} and \textit{I. Loris} [J. Appl. Stat. 40, No. 5, 1090--1105 (2013; Zbl 1514.62770)]. This implies that statistical inference for that family is problematic. Establishing probabilistic properties for this four-parameter family however still makes sense. For the three-parameter family, there is no identification problem. The main contribution in [the authors, ibid. 87, No. 3, 471--504 (2019; Zbl 1528.60018)] is to provide asymptotic results for maximum likelihood and method-of-moments estimators for members of the three-parameter quantile-based asymmetric family of distributions.
{{\copyright} 2020 International Statistical Institute}On recursions for moments of a compound random variable: an approach using an auxiliary counting random variablehttps://zbmath.org/1528.600202024-03-13T18:33:02.981707Z"Kim, Yoora"https://zbmath.org/authors/?q=ai:kim.yooraSummary: We present an identity on moments of a compound random variable by using an auxiliary counting random variable. Based on this identity, we develop a new recurrence formula for obtaining the raw and central moments of any order for a given compound random variable.Letter to the editor: ``On quantile-based asymmetric family of distributions: properties and inference''https://zbmath.org/1528.600212024-03-13T18:33:02.981707Z"Rubio Alvarez, Francisco J."https://zbmath.org/authors/?q=ai:alvarez.francisco-j-rubioSummary: We show that the family of asymmetric distributions studied in a recent publication in the International Statistical Review is equivalent to the family of two-piece distributions. Moreover, we show that the location-scale asymmetric family proposed in that publication is non-identifiable (overparameterised), and it coincides with the family of two-piece distributions after removing the redundant parameters.
{{\copyright} 2020 International Statistical Institute}
Comment to the paper [\textit{I. Gijbels} et al., Int. Stat. Rev. 87, No. 3, 471--504 (2019; Zbl 1528.60018)].\(U\)-statistics on the spherical Poisson spacehttps://zbmath.org/1528.600242024-03-13T18:33:02.981707Z"Bourguin, Solesne"https://zbmath.org/authors/?q=ai:bourguin.solesne"Durastanti, Claudio"https://zbmath.org/authors/?q=ai:durastanti.claudio"Marinucci, Domenico"https://zbmath.org/authors/?q=ai:marinucci.domenico"Peccati, Giovanni"https://zbmath.org/authors/?q=ai:peccati.giovanniSummary: We review a recent stream of research on normal approximations for linear functionals and more general U-statistics of wavelets/needlets coefficients evaluated on a homogeneous spherical Poisson field. We show how, by exploiting results from [\textit{G. Peccati} and \textit{C. Zheng}, Electron. J. Probab. 15, Paper No. 48, 1487--1527 (2010; Zbl 1228.60031)] based on Malliavin calculus and Stein's method, it is possible to assess the rate of convergence to Gaussianity for a triangular array of statistics with growing dimensions. These results can be exploited in a number of statistical applications, such as spherical density estimations, searching for point sources, estimation of variance, and the spherical two-sample problem.
For the entire collection see [Zbl 1350.60005].On the characterization of exchangeable sequences through reverse-martingale empirical distributionshttps://zbmath.org/1528.600302024-03-13T18:33:02.981707Z"Bladt, Martin"https://zbmath.org/authors/?q=ai:bladt.martin"Shaiderman, Dimitry"https://zbmath.org/authors/?q=ai:shaiderman.dimitrySummary: It is a well-known fact that an exchangeable sequence has empirical distributions that form a reverse-martingale. This paper is devoted to the proof of the converse statement. As a byproduct of the proof for the binary case, we introduce and discuss the notion of two-coloring exchangeability.\(U\)-statistics in stochastic geometryhttps://zbmath.org/1528.600462024-03-13T18:33:02.981707Z"Lachièze-Rey, Raphaël"https://zbmath.org/authors/?q=ai:lachieze-rey.raphael"Reitzner, Matthias"https://zbmath.org/authors/?q=ai:reitzner.matthiasSummary: A \(U\)-statistic of order \(k\) with kernel \(f: \mathbb{X}^k \rightarrow \mathbb{R}^d\) over a Poisson process \(\eta\) is defined as
\[
\displaystyle{\sum_{(x_1,\ldots,x_k)}f(x_1,\ldots,x_k),}
\]
where the summation is over \(k\)-tuples of distinct points of \(\eta\), under appropriate integrability assumptions on \(f\). \(U\)-statistics play an important role in stochastic geometry since many interesting functionals can be written as \(U\)-statistics, like intrinsic volumes of intersection processes, characteristics of random geometric graphs, volumes of random simplices, and many others. It turns out that the Wiener-Ito chaos expansion of a \(U\)-statistic is finite and thus Malliavin calculus is a particularly suitable method. Variance estimates, approximation of the covariance structure, and limit theorems which have been out of reach for many years can be derived. In this chapter we state the fundamental properties of \(U\)-statistics and investigate moment formulae. The main object of the chapter is to introduce the available limit theorems.
For the entire collection see [Zbl 1350.60005].Poisson point process convergence and extreme values in stochastic geometryhttps://zbmath.org/1528.600502024-03-13T18:33:02.981707Z"Schulte, Matthias"https://zbmath.org/authors/?q=ai:schulte.matthias.1|schulte.matthias"Thäle, Christoph"https://zbmath.org/authors/?q=ai:thale.christophSummary: Let \(\eta_t\) be a Poisson point process with intensity measure \(t \mu\), \(t > 0\), over a Borel space \(\mathbb{X}\), where \(\mu\) is a fixed measure. Another point process \(\xi_t\) on the real line is constructed by applying a symmetric function \(f\) to every \(k\)-tuple of distinct points of \(\eta_t\). It is shown that \(\xi_t\) behaves after appropriate rescaling like a Poisson point process, as \(t \rightarrow \infty\), under suitable conditions on \(\eta_t\) and \(f\). This also implies Weibull limit theorems for related extreme values. The result is then applied to investigate problems arising in stochastic geometry, including small cells in Voronoi tessellations, random simplices generated by non-stationary hyperplane processes, triangular counts with angular constraints, and non-intersecting \(k\)-flats. Similar results are derived if the underlying Poisson point process is replaced by a binomial point process.
For the entire collection see [Zbl 1350.60005].Poisson generalized Lindley process and its propertieshttps://zbmath.org/1528.600872024-03-13T18:33:02.981707Z"Cha, Ji Hwan"https://zbmath.org/authors/?q=ai:cha.ji-hwan"Badía, F. G."https://zbmath.org/authors/?q=ai:badia.francisco-germanSummary: In spite of the practical usefulness of the nonhomogeneous Poisson process, it still has some restrictions. To overcome these restrictions, the Poisson Lindley process has been recently developed and introduced in
[\textit{J. H. Cha}, Stat. Probab. Lett. 152, 74--81 (2019; Zbl 1451.60050)]. In this paper, we further generalize the Poisson Lindley process, so that the developed counting process model should have the restarting property and it should include the generalized Polya process as a special case. Some basic stochastic properties of the developed counting process model are derived. Dependence properties and stochastic comparisons are also discussed under a more general framework.Loss probability in priority limited processing queueing systemhttps://zbmath.org/1528.600912024-03-13T18:33:02.981707Z"Yashina, Marina"https://zbmath.org/authors/?q=ai:yashina.marina-viktorovna"Tatashev, Alexander"https://zbmath.org/authors/?q=ai:tatashev.alexander-gennadjevich"de Alencar, Marcelo Sampaio"https://zbmath.org/authors/?q=ai:sampaio-de-alencar.marcelo(no abstract)The value of cost-free uncertain evidencehttps://zbmath.org/1528.620012024-03-13T18:33:02.981707Z"Dziurosz-Serafinowicz, Patryk"https://zbmath.org/authors/?q=ai:dziurosz-serafinowicz.patryk"Dziurosz-Serafinowicz, Dominika"https://zbmath.org/authors/?q=ai:dziurosz-serafinowicz.dominikaSummary: We explore the question of whether cost-free \textit{uncertain} evidence is worth waiting for in advance of making a decision. A classical result in Bayesian decision theory, known as the value of evidence theorem, says that, under certain conditions, when you update your credences by conditionalizing on some cost-free and \textit{certain} evidence, the subjective expected utility of obtaining this evidence is never less than the subjective expected utility of not obtaining it. We extend this result to a type of update method, a variant of Judea Pearl's virtual conditionalization, where uncertain evidence is represented as a set of likelihood ratios. Moreover, we argue that focusing on this method rather than on the widely accepted Jeffrey conditionalization enables us to show that, under a fairly plausible assumption, gathering uncertain evidence not only maximizes expected pragmatic utility, but also minimizes expected epistemic disutility (inaccuracy).A battle in the statistics wars: a simulation-based comparison of Bayesian, frequentist and Williamsonian methodologieshttps://zbmath.org/1528.620022024-03-13T18:33:02.981707Z"Radzvilas, Mantas"https://zbmath.org/authors/?q=ai:radzvilas.mantas"Peden, William"https://zbmath.org/authors/?q=ai:peden.william"De Pretis, Francesco"https://zbmath.org/authors/?q=ai:de-pretis.francescoSummary: The debates between Bayesian, frequentist, and other methodologies of statistics have tended to focus on conceptual justifications, sociological arguments, or mathematical proofs of their long run properties. Both Bayesian statistics and frequentist (``classical'') statistics have strong cases on these grounds. In this article, we instead approach the debates in the ``Statistics Wars'' from a largely unexplored angle: simulations of different methodologies' performance in the short to medium run. We used Big Data methods to conduct a large number of simulations using a straightforward decision problem based around tossing a coin with unknown bias and then placing bets. In this simulation, we programmed four players, inspired by Bayesian statistics, frequentist statistics, Jon Williamson's version of Objective Bayesianism, and a player who simply extrapolates from observed frequencies to general frequencies. The last player served a benchmark function: any worthwhile statistical methodology should at least match the performance of simplistic induction. We focused on the performance of these methodologies in guiding the players towards good decisions. Unlike an earlier simulation study of this type, we found no systematic difference in performance between the Bayesian and frequentist players, provided the Bayesian used a flat prior and the frequentist used a low confidence level. The Williamsonian player was also able to perform well given a low confidence level. However, the frequentist and Williamsonian players performed poorly with high confidence levels, while the Bayesian was surprisingly harmed by biased priors. Our study indicates that all three methodologies should be taken seriously by philosophers and practitioners of statistics.Impact assessment of correlated measurement errors using logarithmic-type estimatorshttps://zbmath.org/1528.620032024-03-13T18:33:02.981707Z"Bhushan, Shashi"https://zbmath.org/authors/?q=ai:bhushan.shashi-bhushan"Kumar, Anoop"https://zbmath.org/authors/?q=ai:kumar.anoop-kumar"Shukla, Shivam"https://zbmath.org/authors/?q=ai:shukla.shivamSummary: In survey sampling, several estimation procedures have been proffered by various prominent authors to compute the impact of measurement errors (ME) but the impact of correlated measurement errors (CME) has been computed only by \textit{Shalabh} and \textit{J.-R. Tsai} [Commun. Stat., Simulation Comput. 46, No. 7, 5566--5593 (2017; Zbl 1384.62033)]. This study provides a novel approach to compute the impact of CME through some logarithmic-type estimators using simple random sampling (SRS). The properties of the proffered estimators have been studied and compared with the properties of the conventional estimators. A numerical study and a broad spectrum simulation study are accomplished over real and artificially generated populations to support the theoretical results.New chain imputation methods for estimating population mean in the presence of missing data using two auxiliary variableshttps://zbmath.org/1528.620042024-03-13T18:33:02.981707Z"Bhushan, Shashi"https://zbmath.org/authors/?q=ai:bhushan.shashi-bhushan"Pandey, Abhay Pratap"https://zbmath.org/authors/?q=ai:pandey.abhay-pratapSummary: This article deals with some new chain imputation methods by using two auxiliary variables under missing completely at random (MCAR) approach. The proposed generalized classes of chain imputation methods are tested from the viewpoint of optimality in terms of MSE. The proposed imputation methods can be considered as an efficient extension to the work of
\textit{S. Singh} and \textit{S. Horn} [Metrika 51, No. 3, 267--276 (2000; Zbl 1093.62510)],
\textit{S. Singh} and \textit{B. Deo} [Stat. Pap. 44, No. 4, 555--579 (2003; Zbl 1050.62013)],
\textit{S. Singh} [Statistics 43, No. 5, 499--511 (2009; Zbl 1282.62026)],
\textit{C. Kadilar} and \textit{H. Cingi} [Commun. Stat., Theory Methods 37, No. 14, 2226--2236 (2008; Zbl 1143.62007)] and
\textit{G. Diana} and \textit{P. F. Perri} [Commun. Stat., Theory Methods 39, No. 18, 3245--3251 (2010; Zbl 1202.62008)].
The performance of the proposed chain imputation methods is investigated relative to the conventional chain-type imputation methods. The theoretical results are derived and comparative study is conducted and the results are found to be quite encouraging providing the improvement over the discussed work.Is there a `safe area' where the nonresponse rate has only a modest effect on bias despite non-ignorable nonresponse?https://zbmath.org/1528.620052024-03-13T18:33:02.981707Z"Hedlin, Dan"https://zbmath.org/authors/?q=ai:hedlin.danSummary: Rising nonresponse rates in social surveys make the issue of nonresponse bias contentious. There are conflicting messages about the importance of high response rates and the hazards of low rates. Some articles (e.g. [\textit{R. M. Groves} and \textit{E. Peytcheva}, ``The impact of nonresponse rates on nonresponse bias: a meta-analysis'', Public Opinion Q. 72, No. 2, 167--189 (2008)]) suggest that the response rate is in general not a good predictor of survey quality. Equally, it is well known that nonresponse may induce bias and increase data collection costs. We go back in the history of the literature of nonresponse and suggest a possible reason to the notion that even a rather small nonresponse rate makes the quality of a survey debatable. We also explore the relationship between nonresponse rate and bias, assuming non-ignorable nonresponse and focusing on estimates of totals or means. We show that there is a `safe area' enclosed by the response rate on the one hand and the correlation between the response propensity and the study variable on the other hand; in this area, (1) the response rate does not greatly affect the nonresponse bias, and (2) the nonresponse bias is small.
{{\copyright} 2020 The Authors. International Statistical Review {\copyright} 2020 International Statistical Institute}Modified ratio cum product type exponential estimator of population mean in stratified random samplinghttps://zbmath.org/1528.620062024-03-13T18:33:02.981707Z"Rather, Khalid Ul Islam"https://zbmath.org/authors/?q=ai:rather.khalid-ul-islam"Bouza, Carlos N."https://zbmath.org/authors/?q=ai:bouza-herrera.carlos-narciso"Rizvi, S. E. H."https://zbmath.org/authors/?q=ai:rizvi.s-e-h"Sharma, Manish"https://zbmath.org/authors/?q=ai:sharma.manish-kumar|sharma.manish-kr"Iqbal Jeelani Bhat, M."https://zbmath.org/authors/?q=ai:iqbal-jeelani-bhat.mSummary: In this article, we proposed a novel dual to ratio cum product type exponential estimator in stratified random sampling. The bias and mean square error up to the first degree of approximation of the proposed estimator have been obtained. The proposed estimator has been compared with the unbiased estimator in stratified random sampling, combined ratio and product estimators, dual to combined ratio, and product estimators. Our results showed a great improvement in terms of relative efficiency. Also, the results are supported by empirical studies.Improved estimators of population mean using auxiliary variables in ranked set samplinghttps://zbmath.org/1528.620072024-03-13T18:33:02.981707Z"Singh, Rajesh"https://zbmath.org/authors/?q=ai:singh.rajesh|singh.rajesh-kumar.1|singh.rajesh-pratap|singh.rajesh-kumar"Kumari, Anamika"https://zbmath.org/authors/?q=ai:kumari.anamikaSummary: This paper presents some improved estimators of population mean using auxiliary variables in Ranked Set Sampling. We have derived the expressions for bias and mean square errors up to the first order of approximation and shown that the proposed estimators under optimum conditions are more efficient than other estimators taken in this paper. In an attempt to verify the efficiencies of proposed estimators, theoretical results are supported by empirical study and simulation study for which we have considered two populations.A class of ratio estimators using auxiliary information for the estimation of population mean under stratified samplinghttps://zbmath.org/1528.620082024-03-13T18:33:02.981707Z"Srivastava, Namita"https://zbmath.org/authors/?q=ai:srivastava.namita"Bhadauriya, Anupama"https://zbmath.org/authors/?q=ai:bhadauriya.anupamaSummary: In this paper we proposed a class of ratio estimators using auxiliary information for the estimation of population mean under stratified sampling. The proposed estimator in this work is based on the Yadav and Baghel estimator [\textit{S. K. Yadav} and \textit{S. Baghel}, Rev. Invest. Oper. 42, No. 2, 279--293 (2021; Zbl 1483.62038)]. The expression of the mean square error for this class of estimators is derived and the performance of the proposed estimator is compared with competing estimators. Numerical illustration of efficiency comparison is also worked out in the paper.Smoothing and benchmarking for small area estimationhttps://zbmath.org/1528.620092024-03-13T18:33:02.981707Z"Steorts, Rebecca C."https://zbmath.org/authors/?q=ai:steorts.rebecca-c"Schmid, Timo"https://zbmath.org/authors/?q=ai:schmid.timo"Tzavidis, Nikos"https://zbmath.org/authors/?q=ai:tzavidis.nikosSummary: Small area estimation is concerned with methodology for estimating population parameters associated with a geographic area defined by a cross-classification that may also include non-geographic dimensions. In this paper, we develop constrained estimation methods for small area problems: those requiring smoothness with respect to similarity across areas, such as geographic proximity or clustering by covariates, and benchmarking constraints, requiring weighted means of estimates to agree across levels of aggregation. We develop methods for constrained estimation decision theoretically and discuss their geometric interpretation. The constrained estimators are the solutions to tractable optimisation problems and have closed-form solutions. Mean squared errors of the constrained estimators are calculated via bootstrapping. Our approach assumes the Bayes estimator exists and is applicable to any proposed model. In addition, we give special cases of our techniques under certain distributional assumptions. We illustrate the proposed methodology using web-scraped data on Berlin rents aggregated over areas to ensure privacy.
{{\copyright} 2020 The Authors. International Statistical Review {\copyright} 2020 International Statistical Institute}Generalized double sampling family of estimators for population mean of sensitive variable harnessing non-sensitive auxiliary variable and attributehttps://zbmath.org/1528.620102024-03-13T18:33:02.981707Z"Yadav, Subhash Kumar"https://zbmath.org/authors/?q=ai:yadav.subhash-kumar"Bari, Tarushree"https://zbmath.org/authors/?q=ai:bari.tarushree"Vishwakarma, Gajendra K."https://zbmath.org/authors/?q=ai:vishwakarma.gajendra-kumarSummary: We present an enhanced double sampling generalized type estimator for the population mean of a sensitive research variable using information gathered from non-sensitive auxiliary variables and attribute, using a two-phase sampling procedure. Some special cases of the suggested family of estimators are also discussed. The expressions for bias and mean squared error of the proposed generalized estimators are derived and theoretical comparisons are made with competing estimators. Theoretical results are supported by numerical evidence generated from real-world data. A simulation analysis is also carried out to compare the efficiencies of the proposed and competing family of esimators. Both data sets show that the proposed generalized class of estimators outperforms all other estimators currently in use.A new flexible generalized family for constructing many families of distributionshttps://zbmath.org/1528.620112024-03-13T18:33:02.981707Z"Tahir, M. H."https://zbmath.org/authors/?q=ai:tahir.muhammad-hussain"Hussain, M. Adnan"https://zbmath.org/authors/?q=ai:hussain.muhammad-adnan"Cordeiro, Gauss M."https://zbmath.org/authors/?q=ai:cordeiro.gauss-moutinhoSummary: We propose a \textit{new flexible generalized family} (NFGF) for constructing many families of distributions. The importance of the NFGF is that any baseline distribution can be chosen and it does not involve any additional parameters. Some useful statistical properties of the NFGF are determined such as a linear representation for the family density, analytical shapes of the density and hazard rate, random variable generation, moments and generating function. Further, the structural properties of a special model named the \textit{new flexible Kumaraswamy} (NFKw) distribution, are investigated, and the model parameters are estimated by maximum-likelihood method. A simulation study is carried out to assess the performance of the estimates. The usefulness of the NFKw model is proved empirically by means of three real-life data sets. In fact, the two-parameter NFKw model performs better than three-parameter transmuted-Kumaraswamy, three-parameter exponentiated-Kumaraswamy and the well-known two-parameter Kumaraswamy models.Optimal non-adaptive probabilistic group testing in general sparsity regimeshttps://zbmath.org/1528.620122024-03-13T18:33:02.981707Z"Bay, Wei Heng"https://zbmath.org/authors/?q=ai:bay.wei-heng"Scarlett, Jonathan"https://zbmath.org/authors/?q=ai:scarlett.jonathan"Price, Eric"https://zbmath.org/authors/?q=ai:price.ericSummary: In this paper, we consider the problem of noiseless non-adaptive probabilistic group testing, in which the goal is high-probability recovery of the defective set. We show that in the case of \(n\) items among which \(k\) are defective, the smallest possible number of tests equals \(\min\{C_{k, n} k\log n, n\}\) up to lower-order asymptotic terms, where \(C_{k, n}\) is a uniformly bounded constant (varying depending on the scaling of \(k\) with respect to \(n\)) with a simple explicit expression. The algorithmic upper bound follows from a minor adaptation of an existing analysis of the Definite Defectives algorithm, and the algorithm-independent lower bound builds on existing works for the regimes \(k\leq n^{1-\varOmega(1)}\) and \(k = \varTheta(n)\). In sufficiently sparse regimes (including \(k = o\left(\frac{n}{\log n}\right))\), our main result generalizes that of \textit{A. Coja-Oghlan} et al. [Comb. Probab. Comput. 30, No. 6, 811--848 (2021; Zbl 1511.92030)] by avoiding the assumption \(k\leq n^{1-\varOmega(1)}\), whereas in sufficiently dense regimes (including \(k = \omega\left(\frac{n}{\log n}\right)\)), our main result shows that individual testing is asymptotically optimal for any non-zero target success probability, thus strengthening an existing result of \textit{M. Aldridge} [IEEE Trans. Inf. Theory 65, No. 4, 2058--2061 (2019; Zbl 1432.62036)] in terms of both the error probability and the assumed scaling of \(k\).Small-sample testing inference in symmetric and log-symmetric linear regression modelshttps://zbmath.org/1528.620132024-03-13T18:33:02.981707Z"Medeiros, Francisco M. C."https://zbmath.org/authors/?q=ai:medeiros.francisco-m-c"Ferrari, Silvia L. P."https://zbmath.org/authors/?q=ai:ferrari.silvia-l-de-paulaSummary: This paper deals with the issue of testing hypotheses in symmetric and log-symmetric linear regression models in small and moderate-sized samples. We focus on four tests, namely, the Wald, likelihood ratio, score, and gradient tests. These tests rely on asymptotic results and are unreliable when the sample size is not large enough to guarantee a good agreement between the exact distribution of the test statistic and the corresponding chi-squared asymptotic distribution. Bartlett and Bartlett-type corrections typically attenuate the size distortion of the tests. These corrections are available in the literature for the likelihood ratio and score tests in symmetric linear regression models. Here, we derive a Bartlett-type correction for the gradient test. We show that the corrections are also valid for the log-symmetric linear regression models. We numerically compare the various tests and bootstrapped tests, through simulations. Our results suggest that the corrected and bootstrapped tests exhibit type I probability error closer to the chosen nominal level with virtually no power loss. The analytically corrected tests as well as the bootstrapped tests, including the Bartlett-corrected gradient test derived in this paper, perform with the advantage of not requiring computationally intensive calculations. We present a real data application to illustrate the usefulness of the modified tests.
{{\copyright} 2017 The Authors. Statistica Neerlandica {\copyright} 2017 VVS.}Moment-based estimation for parameters of general inverse subordinatorhttps://zbmath.org/1528.620142024-03-13T18:33:02.981707Z"Grzesiek, Aleksandra"https://zbmath.org/authors/?q=ai:grzesiek.aleksandra"Połoczański, Rafał"https://zbmath.org/authors/?q=ai:poloczanski.rafal"Kumar, Arun"https://zbmath.org/authors/?q=ai:kumar.arun.1"Wyłomańska, Agnieszka"https://zbmath.org/authors/?q=ai:wylomanska.agnieszkaSummary: In recent years the processes with anomalous diffusive dynamics have been widely discussed in the literature. The classic example of the anomalous diffusive models is the continuous time random walk (CTRW) which is a natural generalization of the random walk model. One of the fundamental properties of the classical CTRW is the fact that in the limit it tends to the Brownian motion subordinated by the so-called \(\beta\)-stable subordinator when the mean of waiting times is infinite. One can consider the generalization of such subordinated model by taking general inverse subordinator instead of the \(\beta\)-stable one as a time-change. The inverse subordinator is the first exit time of the non-decreasing Lévy process also called subordinator. In this paper we consider the Brownian motion delayed by general inverse subordinator. The main attention is paid to the estimation method of the parameters of the general inverse subordinator in the considered model. We propose a novel estimation technique based on the discretization of the subordinator's distribution. Using this approach we demonstrate that the distribution of the constant time periods, visible in the trajectory of the considered model, can be described by the so-called modified cumulative distribution function. This paper is an extension of the authors' previous article where a similar approach was applied, however here we focus on moment-based estimation and compare it with other popular methods of estimation. The effectiveness of the new algorithm is verified using the Monte Carlo approach.On solving bias-corrected non-linear estimation equations with an application to the dynamic linear modelhttps://zbmath.org/1528.620152024-03-13T18:33:02.981707Z"Mahmood, Munir"https://zbmath.org/authors/?q=ai:mahmood.munir"King, Maxwell L."https://zbmath.org/authors/?q=ai:king.maxwell-lSummary: In a seminal paper, \textit{T. K. Mak} [J. R. Stat. Soc., Ser. B 55, No. 4, 945--955 (1993; Zbl 0782.62030)] derived an efficient algorithm for solving non-linear unbiased estimation equations. In this paper, we show that when Mak's algorithm is applied to biased estimation equations, it results in the estimates that would come from solving a bias-corrected estimation equation, making it a consistent estimator if regularity conditions hold. In addition, the properties that Mak established for his algorithm also apply in the case of biased estimation equations but for estimates from the bias-corrected equations. The marginal likelihood estimator is obtained when the approach is applied to both maximum likelihood and least squares estimation of the covariance matrix parameters in the general linear regression model. The new approach results in two new estimators when applied to the profile and marginal likelihood functions for estimating the lagged dependent variable coefficient in the dynamic linear regression model. Monte Carlo simulation results show the new approach leads to a better estimator when applied to the standard profile likelihood. It is therefore recommended for situations in which standard estimators are known to be biased.
{{\copyright} 2016 The Authors. Statistica Neerlandica {\copyright} 2016 VVS.}Bayesian robustness modelling using the \(O\)-regularly varying distributionshttps://zbmath.org/1528.620162024-03-13T18:33:02.981707Z"Andrade, J. A. A."https://zbmath.org/authors/?q=ai:andrade.jose-ailton-alencar"Omey, Edward"https://zbmath.org/authors/?q=ai:omey.edwardSummary: The theory of robustness modelling is essentially based on heavy-tailed distributions, because longer tails are more prepared to deal with diverse information (such as outliers) because of the higher probabilities on the tails. There are many classes of distributions that can be regarded as heavy tails; some of them have interesting properties and are not explored in statistics. In the present work, we propose a robustness modelling approach based on the \(O\)-regularly varying class (ORV), which is a generalization of the regular variation family; however, the ORV class allows more flexible tails behaviour, which can improve the way in which the outlying information is discarded by the model. We establish sufficient conditions in the location and in the scale parameter structures, which allow to resolve automatically the conflicts of information. We also provide a procedure for generating new distributions within the ORV class.
{{\copyright} 2017 The Authors. Statistica Neerlandica {\copyright} 2017 VVS.}Likelihood, replicability and Robbins' confidence sequenceshttps://zbmath.org/1528.620172024-03-13T18:33:02.981707Z"Pace, Luigi"https://zbmath.org/authors/?q=ai:pace.luigi"Salvan, Alessandra"https://zbmath.org/authors/?q=ai:salvan.alessandraSummary: The widely claimed replicability crisis in science may lead to revised standards of significance. The customary frequentist confidence intervals, calibrated through hypothetical repetitions of the experiment that is supposed to have produced the data at hand, rely on a feeble concept of replicability. In particular, contradictory conclusions may be reached when a substantial enlargement of the study is undertaken. To redefine statistical confidence in such a way that inferential conclusions are non-contradictory, with large enough probability, under enlargements of the sample, we give a new reading of a proposal dating back to the 60s, namely, Robbins' confidence sequences. Directly bounding the probability of reaching, in the future, conclusions that contradict the current ones, Robbins' confidence sequences ensure a clear-cut form of replicability when inference is performed on accumulating data. Their main frequentist property is easy to understand and to prove. We show that Robbins' confidence sequences may be justified under various views of inference: they are likelihood-based, can incorporate prior information and obey the strong likelihood principle. They are easy to compute, even when inference is on a parameter of interest, especially using a closed form approximation from normal asymptotic theory.
{{\copyright} 2019 The Authors. International Statistical Review {\copyright} 2019 International Statistical Institute}Robust maximum likelihood estimationhttps://zbmath.org/1528.620182024-03-13T18:33:02.981707Z"Bertsimas, Dimitris"https://zbmath.org/authors/?q=ai:bertsimas.dimitris-j"Nohadani, Omid"https://zbmath.org/authors/?q=ai:nohadani.omidSummary: In many applications, statistical estimators serve to derive conclusions from data, for example, in finance, medical decision making, and clinical trials. However, the conclusions are typically dependent on uncertainties in the data. We use robust optimization principles to provide robust maximum likelihood estimators that are protected against data errors. Both types of input data errors are considered: (a) the adversarial type, modeled using the notion of uncertainty sets, and (b) the probabilistic type, modeled by distributions. We provide efficient local and global search algorithms to compute the robust estimators and discuss them in detail for the case of multivariate normally distributed data. The estimator performance is demonstrated on two applications. First, using computer simulations, we demonstrate that the proposed estimators are robust against both types of data uncertainty and provide more accurate estimates compared with classical estimators, which degrade significantly, when errors are encountered. We establish a range of uncertainty sizes for which robust estimators are superior. Second, we analyze deviations in cancer radiation therapy planning. Uncertainties among plans are caused by patients' individual anatomies and the trial-and-error nature of the process. When analyzing a large set of past clinical treatment data, robust estimators lead to more reliable decisions when applied to a large set of past treatment plans.On the robustness to adversarial corruption and to heavy-tailed data of the Stahel-Donoho median of meanshttps://zbmath.org/1528.620192024-03-13T18:33:02.981707Z"Depersin, Jules"https://zbmath.org/authors/?q=ai:depersin.jules"Lecué, Guillaume"https://zbmath.org/authors/?q=ai:lecue.guillaumeSummary: We consider median of means (MOM) versions of the Stahel-Donoho outlyingness (SDO) [\textit{D. L. Donoho}, ``Breakdown properties of multivariate location estimators'', Techn. Rep., Harvard Univ. (1982); \textit{W. A. Stahel}, Robuste Schätzungen: Infinitesimale Optimalität und Schätzungen von Kovarianzmatrizen. Zürich: Eidgenössische Technische Hochschule Zürich (Diss.) (1981; Zbl 0531.62036)] and of the Median Absolute Deviation (MAD) [\textit{F. R. Hampel}, Z. Wahrscheinlichkeitstheor. Verw. Geb. 27, 87--104 (1973; Zbl 0255.62045)] functions to construct subgaussian estimators of a mean vector under adversarial contamination and heavy-tailed data. We develop a single analysis of the MOM version of the SDO which covers all cases ranging from the Gaussian case to the \(L_2\) case. It is based on isomorphic and almost isometric properties of the MOM versions of SDO and MAD. This analysis also covers cases where the mean does not even exist but a location parameter does; in those cases we still recover the same subgaussian rates and the same price for adversarial contamination even though there is not even a first moment. These properties are achieved by the classical SDO median and are therefore the first non-asymptotic statistical bounds on the Stahel-Donoho median complementing the \(\sqrt{n}\)-consistency [\textit{R. A. Maronna} and \textit{V. J. Yohai}, J. Am. Stat. Assoc. 90, No. 429, 330--341 (1995; Zbl 0820.62050)] and asymptotic normality [\textit{Y. Zuo} et al., Ann. Stat. 32, No. 1, 167--188 (2004; Zbl 1105.62349)] of the Stahel-Donoho estimators. We also show that the MOM version of MAD can be used to construct an estimator of the covariance matrix only under the existence of a second moment or of a scatter matrix if a second moment does not exist.Uniformly complete consistency of frequency polygon estimation for dependent samples and an applicationhttps://zbmath.org/1528.620202024-03-13T18:33:02.981707Z"Wu, Yi"https://zbmath.org/authors/?q=ai:wu.yi"Wang, Xuejun"https://zbmath.org/authors/?q=ai:wang.xuejunSummary: The frequency polygon estimation, which is based on histogram technique, has a similar convergence rate as those of modern non-negative kernel estimators and the advantage of computational simplicity. This paper will study the uniformly complete consistency and the rates of uniformly complete consistency of frequency polygon estimation for widely orthant dependent samples under some general conditions, which improve and extend the corresponding ones in the literature. As an application, the uniformly complete consistency and the corresponding rates of hazard rate function estimator are also obtained.Spline regression for hazard rate estimation when data are censored and measured with errorhttps://zbmath.org/1528.620212024-03-13T18:33:02.981707Z"Comte, Fabienne"https://zbmath.org/authors/?q=ai:comte.fabienne"Mabon, Gwennaelle"https://zbmath.org/authors/?q=ai:mabon.gwennaelle"Samson, Adeline"https://zbmath.org/authors/?q=ai:samson.adelineSummary: In this paper, we study an estimation problem where the variables of interest are subject to both right censoring and measurement error. In this context, we propose a nonparametric estimation strategy of the hazard rate, based on a regression contrast minimized in a finite-dimensional functional space generated by splines bases. We prove a risk bound of the estimator in terms of integrated mean square error and discuss the rate of convergence when the dimension of the projection space is adequately chosen. Then we define a data-driven criterion of model selection and prove that the resulting estimator performs an adequate compromise. The method is illustrated via simulation experiments that show that the strategy is successful.
{{\copyright} 2017 The Authors. Statistica Neerlandica {\copyright} 2017 VVS.}Non-parametric regression in clustered multistate current status data with informative cluster sizehttps://zbmath.org/1528.620222024-03-13T18:33:02.981707Z"Lan, Ling"https://zbmath.org/authors/?q=ai:lan.ling"Bandyopadhyay, Dipankar"https://zbmath.org/authors/?q=ai:bandyopadhyay.dipankar"Datta, Somnath"https://zbmath.org/authors/?q=ai:datta.somnathSummary: Datasets examining periodontal disease records current (disease) status information of tooth-sites, whose stochastic behavior can be attributed to a multistate system with state occupation determined at a single inspection time. In addition, the tooth-sites remain clustered within a subject, and the number of available tooth-sites may be representative of the true periodontal disease status of that subject, leading to an `informative cluster size' scenario. To provide insulation against incorrect model assumptions, we propose a non-parametric regression framework to estimate state occupation probabilities at a given time and state exit/entry distributions, utilizing weighted monotonic regression and smoothing techniques. We demonstrate the superior performance of our proposed weighted estimators over the unweighted counterparts via a simulation study and illustrate the methodology using a dataset on periodontal disease.
{{\copyright} 2016 The Authors. Statistica Neerlandica {\copyright} 2016 VVS.}Asymptotics and smoothing parameter selection for penalized spline regression with various loss functionshttps://zbmath.org/1528.620232024-03-13T18:33:02.981707Z"Yoshida, Takuma"https://zbmath.org/authors/?q=ai:yoshida.takumaSummary: Penalized splines are used in various types of regression analyses, including non-parametric quantile, robust and the usual mean regression. In this paper, we focus on the penalized spline estimator with general convex loss functions. By specifying the loss function, we can obtain the mean estimator, quantile estimator and robust estimator. We will first study the asymptotic properties of penalized splines. Specifically, we will show the asymptotic bias and variance as well as the asymptotic normality of the estimator. Next, we will discuss smoothing parameter selection for the minimization of the mean integrated squares error. The new smoothing parameter can be expressed uniquely using the asymptotic bias and variance of the penalized spline estimator. To validate the new smoothing parameter selection method, we will provide a simulation. The simulation results show that the consistency of the estimator with the proposed smoothing parameter selection method can be confirmed and that the proposed estimator has better behavior than the estimator with generalized approximate cross-validation. A real data example is also addressed.
{{\copyright} 2016 The Authors. Statistica Neerlandica {\copyright} 2016 VVS.}Statistical inference on restricted partial linear regression models with partial distortion measurement errorshttps://zbmath.org/1528.620242024-03-13T18:33:02.981707Z"Zhang, Jun"https://zbmath.org/authors/?q=ai:zhang.jun.10"Zhou, Nanguang"https://zbmath.org/authors/?q=ai:zhou.nanguang"Sun, Zipeng"https://zbmath.org/authors/?q=ai:sun.zipeng"Li, Gaorong"https://zbmath.org/authors/?q=ai:li.gaorong"Wei, Zhenghong"https://zbmath.org/authors/?q=ai:wei.zhenghongSummary: We consider the estimation and hypothesis testing problems for the partial linear regression models when some variables are distorted with errors by some unknown functions of commonly observable confounding variable. The proposed estimation procedure is designed to accommodate undistorted as well as distorted variables. To test a hypothesis on the parametric components, a restricted least squares estimator is proposed under the null hypothesis. Asymptotic properties for the estimators are established. A test statistic based on the difference between the residual sums of squares under the null and alternative hypotheses is proposed, and we also obtain the asymptotic properties of the test statistic. A wild bootstrap procedure is proposed to calculate critical values. Simulation studies are conducted to demonstrate the performance of the proposed procedure, and a real example is analyzed for an illustration.
{{\copyright} 2016 The Authors. Statistica Neerlandica {\copyright} 2016 VVS.}Graphical comparison of high-dimensional distributionshttps://zbmath.org/1528.620252024-03-13T18:33:02.981707Z"Modarres, Reza"https://zbmath.org/authors/?q=ai:modarres.rezaSummary: We consider groups of observations in \(\mathbb{R}^d\) and present a simultaneous plot of the empirical cumulative distribution functions of the within and between interpoint distances to visualise and examine the equality of the underlying distribution functions of the observations. We provide several examples to illustrate how such plots can be utilised to envision and canvass the relationship between the two distributions under location, scale, dependence and shape changes. We suggest new statistics for testing the equality of \(k\) distributions and extend the simultaneous plots to visualise them. We compare the new statistics to existing tests based on the interpoint distances.
{{\copyright} 2020 The Authors. International Statistical Review {\copyright} 2020 International Statistical Institute}On variable ordination of modified Cholesky decomposition for estimating time-varying covariance matriceshttps://zbmath.org/1528.620262024-03-13T18:33:02.981707Z"Kang, Xiaoning"https://zbmath.org/authors/?q=ai:kang.xiaoning"Deng, Xinwei"https://zbmath.org/authors/?q=ai:deng.xinwei"Tsui, Kam-Wah"https://zbmath.org/authors/?q=ai:tsui.kam-wah"Pourahmadi, Mohsen"https://zbmath.org/authors/?q=ai:pourahmadi.mohsenSummary: Estimating time-varying covariance matrices of the vector of interest is challenging both computationally and statistically due to a large number of constrained parameters. In this work, we consider an order-averaged Cholesky-log-GARCH (OA-CLGARCH) model for estimating time-varying covariance matrices through the orthogonal transformations of the vector based on the modified Cholesky decomposition. The proposed method is to transform the vector at each time as a linear transformation of uncorrelated latent variables and then to use simple univariate GARCH models to model them separately. But the modified Cholesky decomposition relies on a given order of variables, which is often not available, to sequentially orthogonalize the variables. The proposed method develops an order-averaged strategy for the Cholesky-GARCH method to alleviate the effect of order of variables. The merits of the proposed method are illustrated through simulations and real-data studies.
{{\copyright} 2019 The Authors. International Statistical Review {\copyright} 2019 International Statistical Institute}A review of envelope modelshttps://zbmath.org/1528.620272024-03-13T18:33:02.981707Z"Lee, Minji"https://zbmath.org/authors/?q=ai:lee.minji"Su, Zhihua"https://zbmath.org/authors/?q=ai:su.zhihuaSummary: The envelope model was first introduced as a parsimonious version of multivariate linear regression. It uses dimension reduction techniques to remove immaterial variation in the data and has the potential to gain efficiency in estimation and improve prediction. Many advances have taken place since its introduction, and the envelope model has been applied to many contexts in multivariate analysis, including partial least squares, generalised linear models, Bayesian analysis, variable selection and quantile regression, among others. This article serves as a review of the envelope model and its developments for those who are new to the area.
{{\copyright} 2020 The Authors. International Statistical Review {\copyright} 2020 International Statistical Institute}Unsupervised feature selection via data reconstruction and side informationhttps://zbmath.org/1528.620282024-03-13T18:33:02.981707Z"Zhang, Rui"https://zbmath.org/authors/?q=ai:zhang.rui.23"Li, Xuelong"https://zbmath.org/authors/?q=ai:li.xuelongEditorial remark: No review copy delivered.Bartlett correction to the likelihood ratio test for MCAR with two-step monotone samplehttps://zbmath.org/1528.620292024-03-13T18:33:02.981707Z"Shutoh, Nobumichi"https://zbmath.org/authors/?q=ai:shutoh.nobumichi"Nishiyama, Takahiro"https://zbmath.org/authors/?q=ai:nishiyama.takahiro"Hyodo, Masashi"https://zbmath.org/authors/?q=ai:hyodo.masashiSummary: Assuming that two-step monotone missing data is drawn from a multivariate normal population, this paper derives the Bartlett-type correction to the likelihood ratio test for missing completely at random (MCAR), which plays an important role in the statistical analysis of incomplete datasets. The advantages of our approach are confirmed in Monte Carlo simulations. Our correction drastically improved the accuracy of the type I error in \textit{R. J. A. Little}'s [J. Am. Stat. Assoc. 83, No. 404, 1198--1202 (1988; \url{doi:10.1080/01621459.1988.10478722})] test for MCAR and performed well even on moderate sample sizes.
{{\copyright} 2017 The Authors. Statistica Neerlandica {\copyright} 2017 VVS.}Bayesian model selection of Gaussian directed acyclic graph structureshttps://zbmath.org/1528.620302024-03-13T18:33:02.981707Z"Castelletti, Federico"https://zbmath.org/authors/?q=ai:castelletti.federicoSummary: During the last years, graphical models have become a popular tool to represent dependencies among variables in many scientific areas. Typically, the objective is to dependence relationships that can be represented through a directed acyclic graph (DAG). The set of all conditional independencies encoded by a DAG determines its Markov property. In general, DAGs encoding the same conditional independencies are not distinguishable from observational data and can be collected into equivalence classes, each one represented by a chain graph called essential graph (EG). However, both the DAG and EG space grow super exponentially in the number of variables, and so, graph structural learning requires the adoption of Markov chain Monte Carlo (MCMC) techniques. In this paper, we review some recent results on Bayesian model selection of Gaussian DAG models under a unified framework. These results are based on closed-form expressions for the marginal likelihood of a DAG and EG structure, which is obtained from a few suitable assumptions on the prior for model parameters. We then introduce a general MCMC scheme that can be adopted both for model selection of DAGs and EGs together with a couple of applications on real data sets.
{{\copyright} 2020 International Statistical Institute.}Robust kernel principal component analysis with optimal meanhttps://zbmath.org/1528.620312024-03-13T18:33:02.981707Z"Li, Pei"https://zbmath.org/authors/?q=ai:li.pei"Zhang, Wenlin"https://zbmath.org/authors/?q=ai:zhang.wenlin"Lu, Chengjun"https://zbmath.org/authors/?q=ai:lu.chengjun"Zhang, Rui"https://zbmath.org/authors/?q=ai:zhang.rui.23"Li, Xuelong"https://zbmath.org/authors/?q=ai:li.xuelongSummary: The kernel principal component analysis (KPCA) serves as an efficient approach for dimensionality reduction. However, the KPCA method is sensitive to the outliers since the large square errors tend to dominate the loss of KPCA. To strengthen the robustness of KPCA method, we propose a novel robust kernel principal component analysis with optimal mean (RKPCA-OM) method. RKPCA-OM not only possesses stronger robustness for outliers than the conventional KPCA method, but also can eliminate the optimal mean automatically. What is more, the theoretical proof proves the convergence of the algorithm to guarantee that the optimal subspaces and means are obtained. Lastly, exhaustive experimental results verify the superiority of our method.Combining homogeneous groups of preclassified observations with application to international tradehttps://zbmath.org/1528.620322024-03-13T18:33:02.981707Z"Cerasa, Andrea"https://zbmath.org/authors/?q=ai:cerasa.andreaSummary: This article proposes three methods for merging homogeneous clusters of observations that are grouped according to a pre-existing (known) classification. This clusterwise regression problem is at the very least compelling in analyzing international trade data, where transaction prices can be grouped according to the corresponding origin-destination combination. A proper merging of these prices could simplify the analysis of the market without affecting the representativeness of the data and highlight commercial anomalies that may hide frauds. The three algorithms proposed are based on an iterative application of the \(F\)-test and have the advantage of being extremely flexible, as they do not require to predetermine the number of final clusters, and their output depends only on a tuning parameter. Monte Carlo results show very good performances of all the procedures, whereas the application to a couple of empirical data sets proves the practical utility of the methods proposed for reducing the dimension of the market and isolating suspicious commercial behaviors.
{{\copyright} 2016 The Authors Statistica Neerlandica published by John Wiley \& Sons Ltd on behalf of Netherlands Society for Statistics and Operations Research}A competitive optimization approach for data clustering and orthogonal non-negative matrix factorizationhttps://zbmath.org/1528.620332024-03-13T18:33:02.981707Z"Dehghanpour-Sahron, Ja'far"https://zbmath.org/authors/?q=ai:dehghanpour-sahron.jafar"Mahdavi-Amiri, Nezam"https://zbmath.org/authors/?q=ai:mahdavi-amiri.nezamSummary: Partitioning a given data-set into subsets based on similarity among the data is called clustering. Clustering is a major task in data mining and machine learning having many applications such as text retrieval, pattern recognition, and web mining. Here, we briefly review some clustering related problems (\(k\)-means, normalized \(k\)-cut, orthogonal non-negative matrix factorization, ONMF, and isoperimetry) and describe their connections. We formulate the relaxed mean version of the isoperimetry problem as an optimization problem with non-negative orthogonal constraints. We first make use of a gradient-based optimization algorithm to solve this kind of a problem, and then apply a post-processing technique to extract a solution of the clustering problem. Also, we propose a simplified approach to improve upon solution of the 2-dimensional clustering problem, using the \(N\)-nearest neighbor graph. Inspired by this technique, we apply a multilevel method for clustering a given data-set to reduce the size of the problem by grouping a number of similar vertices. The number is determined based on two values, namely, the maximum and the average of the edge weights of the vertices connected to a selected vertex. In addition, using the connections between ONMF and \(k\)-means and between \(k\)-means and the isoperimetry problem, we propose an algorithm to solve the ONMF problem. A comparative performance analysis of our approach with other related methods shows outperformance of our approach, in terms of the obtained misclassification error rate and Rand index, on both benchmark and randomly generated problems as well as hard synthetic data-sets.Deep low-rank matrix factorization with latent correlation estimation for micro-video multi-label classificationhttps://zbmath.org/1528.620342024-03-13T18:33:02.981707Z"Su, Yuting"https://zbmath.org/authors/?q=ai:su.yuting"Xu, Junyu"https://zbmath.org/authors/?q=ai:xu.junyu"Hong, Daozheng"https://zbmath.org/authors/?q=ai:hong.daozheng"Fan, Fugui"https://zbmath.org/authors/?q=ai:fan.fugui"Zhang, Jing"https://zbmath.org/authors/?q=ai:zhang.jing.214"Jing, Peiguang"https://zbmath.org/authors/?q=ai:jing.peiguangSummary: Currently, micro-videos are becoming an increasingly prevailing form of user-generated contents (UGCs) on various social platforms. Several studies have been conducted to explore the semantics of micro-videos and the behavior of individuals for various tasks, such as venue categorization, popularity prediction, and personalized recommendation. However, few studies have been dedicated to solving micro-video multi-label classification. More importantly, learning intrinsic and robust feature representations for micro-videos is still a complicated and challenging problem. In this paper, we propose a deep matrix factorization with latent correlation estimation (DMFLCE) for micro-video multi-label classification. In DMFLCE, we develop a deep matrix factorization component constrained by a low-rank constraint to learn the lowest-rank representations for micro-videos and the intrinsic characterizations for latent attributes simultaneously. To explicitly exhibit the dependencies of the learned latent attributes and labels for improved classification performance, we construct two inverse covariance estimation components to automatically encode correlation patterns with respect to the latent attributes and labels. Experiments conducted on a publicly available large-scale micro-video dataset demonstrate the effectiveness of our proposed method compared with state-of-the-art methods.Penalty and related estimation strategies in the spatial error modelhttps://zbmath.org/1528.620352024-03-13T18:33:02.981707Z"Al-Momani, Marwan"https://zbmath.org/authors/?q=ai:al-momani.marwan-a"Hussein, Abdulkadir A."https://zbmath.org/authors/?q=ai:hussein.abdulkadir-a"Ahmed, S. E."https://zbmath.org/authors/?q=ai:ahmed.syed-ejazSummary: Spatial autoregressive models are powerful tools in the analysis of data sets from diverse scientific areas of research such as econometrics, plant species richness, cancer mortality rates, image processing, analysis of the functional Magnetic Resonance Imaging (fMRI) data, and many more. An important class in the host of spatial autoregressive models is the class of spatial error models in which spatially lagged error terms are assumed. In this paper, we propose efficient shrinkage and penalty estimators for the regression coefficients of the spatial error model. We carry out asymptotic as well as simulation analyses to illustrate the gain in efficiency achieved by these new estimators. Furthermore, we apply the new methodology to housing prices data and provide a bootstrap approach to compute prediction errors of the new estimators.
{{\copyright} 2016 The Authors. Statistica Neerlandica {\copyright} 2016 VVS.}Algorithms for generalized clusterwise linear regressionhttps://zbmath.org/1528.620362024-03-13T18:33:02.981707Z"Park, Young Woong"https://zbmath.org/authors/?q=ai:park.young-woong|park.youngwoong"Jiang, Yan"https://zbmath.org/authors/?q=ai:jiang.yan"Klabjan, Diego"https://zbmath.org/authors/?q=ai:klabjan.diego"Williams, Loren"https://zbmath.org/authors/?q=ai:williams.lorenSummary: Clusterwise linear regression (CLR), a clustering problem intertwined with regression, finds clusters of entities such that the overall sum of squared errors from regressions performed over these clusters is minimized, where each cluster may have different variances. We generalize the CLR problem by allowing each entity to have more than one observation and refer to this as generalized CLR. We propose an exact mathematical programming-based approach relying on column generation, a column generation-based heuristic algorithm that clusters predefined groups of entities, a metaheuristic genetic algorithm with adapted Lloyd's algorithm for \(K\)-means clustering, a two-stage approach, and a modified algorithm of Späth [\textit{H. Späth}, Algorithm 39: Clusterwise linear regression. Computing 22, 367--373 (1979; Zbl 0387.65028)] for solving generalized CLR. We examine the performance of our algorithms on a stock-keeping unit (SKU)-clustering problem employed in forecasting halo and cannibalization effects in promotions using real-world retail data from a large supermarket chain. In the SKU clustering problem, the retailer needs to cluster SKUs based on their seasonal effects in response to promotions. The seasonal effects result from regressions with predictors being promotion mechanisms and seasonal dummies performed over clusters generated. We compare the performance of all proposed algorithms for the SKU problem with real-world and synthetic data.A geometrical interpretation of collinearity: a natural way to justify ridge regression and its anomalieshttps://zbmath.org/1528.620372024-03-13T18:33:02.981707Z"García-Pérez, José"https://zbmath.org/authors/?q=ai:garcia-perez.jose"del Mar López-Martín, María"https://zbmath.org/authors/?q=ai:lopez-martin.maria-del-mar"García-García, Catalina"https://zbmath.org/authors/?q=ai:garcia.catalina-garcia|garcia-garcia.catalina-beatriz"Salmerón-Gómez, Román"https://zbmath.org/authors/?q=ai:salmeron-gomez.romanSummary: Justifying ridge regression from a geometrical perspective is one of the main contributions of this paper. To the best of our knowledge, this question has not been treated previously. This paper shows that ridge regression is a particular case of raising procedures that provide greater flexibility by transforming the matrix \(\mathbf{X}\) associated with the model. Thus, raising procedures, based on a geometrical idea of the vectorial space associated with the columns of matrix \(\mathbf{X}\), lead naturally to ridge regression and justify the presence of the well-known constant \(k\) on the main diagonal of matrix \(\mathbf{X}^\prime\mathbf{X}\). This paper also analyses and compares different alternatives to raising with respect to collinearity mitigation. The results are illustrated with an empirical application.
{{\copyright} 2020 The Authors. International Statistical Review {\copyright} 2020 International Statistical Institute}A skew-normal copula-driven GLMMhttps://zbmath.org/1528.620382024-03-13T18:33:02.981707Z"Das, Kalyan"https://zbmath.org/authors/?q=ai:das.kalyan"Elmasri, Mohamad"https://zbmath.org/authors/?q=ai:elmasri.mohamad"Sen, Arusharka"https://zbmath.org/authors/?q=ai:sen.arusharkaSummary: This paper presents a method for fitting a copula-driven generalized linear mixed models. For added flexibility, the skew-normal copula is adopted for fitting. The correlation matrix of the skew-normal copula is used to capture the dependence structure within units, while the fixed and random effects coefficients are estimated through the mean of the copula. For estimation, a Monte Carlo expectation-maximization algorithm is developed. Simulations are shown alongside a real data example from the Framingham Heart Study.
{{\copyright} 2016 The Authors. Statistica Neerlandica {\copyright} 2016 VVS.}Robust transfer learning of high-dimensional generalized linear modelhttps://zbmath.org/1528.620392024-03-13T18:33:02.981707Z"Sun, Fei"https://zbmath.org/authors/?q=ai:sun.fei.1|sun.fei"Zhang, Qi"https://zbmath.org/authors/?q=ai:zhang.qi.13Summary: This paper studies transfer learning of a high-dimensional generalized linear model with the target model as well as source data from different but possibly related models. Both known and unknown transferable domain settings are considered. On the one hand, an improved two-step transfer learning algorithm is proposed and the optimal rate of convergence for estimation is proved when the set of transferable domain is known. On the other hand, when the set of transferable domain is unknown, we propose a data-driven procedure for transfer learning, called Stepwise Selection algorithm, and investigate its finite-sample performance through simulations studies. Experimental results on six datasets demonstrate that the proposed method can perform better.Multiple testing and variable selection along the path of the least angle regressionhttps://zbmath.org/1528.620402024-03-13T18:33:02.981707Z"Azaïs, Jean-Marc"https://zbmath.org/authors/?q=ai:azais.jean-marc"De Castro, Yohann"https://zbmath.org/authors/?q=ai:de-castro.yohannSummary: We investigate multiple testing and variable selection using the Least Angle Regression (LARS) algorithm in high dimensions under the assumption of Gaussian noise. LARS is known to produce a piecewise affine solution path with change points referred to as the \textit{knots of the LARS path}. The key to our results is an expression in closed form of the exact joint law of a \(K\)-tuple of knots conditional on the variables selected by LARS, the so-called \textit{post-selection} joint law of the LARS knots. Numerical experiments demonstrate the perfect fit of our findings. This paper makes three main contributions. First, we build testing procedures on variables entering the model along the LARS path in the general design case when the noise level can be unknown. These testing procedures are referred to as the Generalized \(t\)-Spacing tests and we prove that they have an exact non-asymptotic level (i.e. the Type I error is exactly controlled). This extends work of \textit{R. J. Tibshirani} et al. [J. Am. Stat. Assoc. 111, No. 514, 600--620 (2016; \url{doi:10.1080/01621459.2015.1108848})] where the spacing test works for consecutive knots and known variance. Second, we introduce a new exact multiple testing procedure after model selection in the general design case when the noise level may be unknown. We prove that this testing procedure has exact non-asymptotic level for general design and unknown noise level. Third, we prove exact control of the false discovery rate under orthogonal design assumption. Monte-Carlo simulations and a real data experiment are provided to illustrate our results in this case. Of independent interest, we introduce an equivalent formulation of the LARS algorithm based on a recursive function.Some monotonicity results for stochastic kriging metamodels in sequential settingshttps://zbmath.org/1528.620412024-03-13T18:33:02.981707Z"Wang, Bing"https://zbmath.org/authors/?q=ai:wang.bing.3|wang.bing.1"Hu, Jiaqiao"https://zbmath.org/authors/?q=ai:hu.jiaqiaoSummary: Stochastic Kriging (SK) and stochastic kriging with gradient estimators (SKG) are useful methods for effectively approximating the response surface of a simulation model. In this paper, we show that in a fully sequential setting when all model parameters are known, the mean squared errors of the optimal SK and SKG predictors are monotonically decreasing as the number of design points increases. In addition, we prove, under appropriate conditions, that the use of gradient information in the SKG framework generally improves the prediction performance of SK. Motivated by these findings, we propose a sequential procedure for adaptively choosing design points and simulation replications in obtaining SK (SKG) predictors with desired levels of fidelity. We justify the validity of the procedure and carry out numerical experiments to illustrate its performance.A negative binomial autoregression with a linear conditional variance-to-mean functionhttps://zbmath.org/1528.620422024-03-13T18:33:02.981707Z"Almohaimeed, Bader S."https://zbmath.org/authors/?q=ai:almohaimeed.bader-sSummary: A general integer-valued time-series model with a conditional variance proportional to the conditional mean is proposed. Specifically, the conditional distribution is a Poisson mixture with a dependent mixing sequence, which results in a negative binomial distribution with a linear conditional variance-to-mean relationship. In addition, the conditional mean is specified as a general parametric function of past observations. We first propose stationarity, ergodicity, and finite moment conditions for the model. Furthermore, the parameters are estimated using the Poisson quasi-maximum likelihood estimate, whose asymptotic properties are studied under weak conditions. Illustrations of the proposed methodology on simulated and actual time series of counts are given.Poisson-geometric INAR(1) process for modeling count time series with overdispersionhttps://zbmath.org/1528.620432024-03-13T18:33:02.981707Z"Bourguignon, Marcelo"https://zbmath.org/authors/?q=ai:bourguignon.marceloSummary: In this paper, we propose a new first-order non-negative integer-valued autoregressive [INAR(1)] process with Poisson-geometric marginals based on binomial thinning for modeling integer-valued time series with overdispersion. Also, the new process has, as a particular case, the Poisson INAR(1) and geometric INAR(1) processes. The main properties of the model are derived, such as probability generating function, moments, conditional distribution, higher-order moments, and jumps. Estimators for the parameters of process are proposed, and their asymptotic properties are established. Some numerical results of the estimators are presented with a discussion of the obtained results. Applications to two real data sets are given to show the potentiality of the new process.
{{\copyright} 2015 The Author. Statistica Neerlandica {\copyright} 2015 VVS.}Multivariate Wold decompositions: a Hilbert \(A\)-module approachhttps://zbmath.org/1528.620442024-03-13T18:33:02.981707Z"Cerreia-Vioglio, Simone"https://zbmath.org/authors/?q=ai:cerreia-vioglio.simone"Ortu, Fulvio"https://zbmath.org/authors/?q=ai:ortu.fulvio"Severino, Federico"https://zbmath.org/authors/?q=ai:severino.federico"Tebaldi, Claudio"https://zbmath.org/authors/?q=ai:tebaldi.claudioSummary: Orthogonal decompositions are essential tools for the study of weakly stationary time series. Some examples are given by the classical Wold decomposition of \textit{H. Wold} [A study in the analysis of stationary time series. Diss. Uppsala, Almqvist \& Wiksells (1938; JFM 64.1200.02)] and the extended Wold decomposition of
the second author et al. [Quant. Econ. 11, No. 1, 203--230 (2020; \url{doi:10.3982/QE994})], which permits to disentangle shocks with heterogeneous degrees of persistence from a given weakly stationary process. The analysis becomes more involved when dealing with vector processes because of the presence of different simultaneous shocks. In this paper, we recast the standard treatment of multivariate time series in terms of Hilbert \(A\)-modules (where matrices replace the field of scalars) and we prove the abstract Wold theorem for self-dual pre-Hilbert \(A\)-modules with an isometric operator. This theorem allows us to easily retrieve the multivariate classical Wold decomposition and the multivariate version of the extended Wold decomposition. The theory helps in handling matrix coefficients and computing orthogonal projections on closed submodules. The orthogonality notion is key to decompose the given vector process into uncorrelated subseries, and it implies a variance decomposition.Markov switching quantile autoregressionhttps://zbmath.org/1528.620452024-03-13T18:33:02.981707Z"Liu, Xiaochun"https://zbmath.org/authors/?q=ai:liu.xiaochunSummary: This paper considers the location-scale quantile autoregression in which the location and scale parameters are subject to regime shifts. The regime changes in lower and upper tails are determined by the outcome of a latent, discrete-state Markov process. The new method provides direct inference and estimate for different parts of a non-stationary time series distribution. Bayesian inference for switching regimes within a quantile, via a three-parameter asymmetric Laplace distribution, is adapted and designed for parameter estimation. Using the Bayesian output, the marginal likelihood is readily available for testing the presence and the number of regimes. The simulation study shows that the predictability of regimes and conditional quantiles by using asymmetric Laplace distribution as the likelihood is fairly comparable with the true model distributions. However, ignoring that autoregressive coefficients might be quantile dependent leads to substantial bias in both regime inference and quantile prediction. The potential of this new approach is illustrated in the empirical applications to the US inflation and real exchange rates for asymmetric dynamics and the S\&P 500 index returns of different frequencies for financial market risk assessment.
{{\copyright} 2016 The Authors. Statistica Neerlandica {\copyright} 2016 VVS.}Diagnostic analysis for a vector autoregressive model under Student's \(t\)-distributionshttps://zbmath.org/1528.620462024-03-13T18:33:02.981707Z"Liu, Yonghui"https://zbmath.org/authors/?q=ai:liu.yonghui"Sang, Ruochen"https://zbmath.org/authors/?q=ai:sang.ruochen"Liu, Shuangzhe"https://zbmath.org/authors/?q=ai:liu.shuangzheSummary: In this paper, we use the local influence method to study a vector autoregressive model under Student's \(t\)-distributions. We present the maximum likelihood estimators and the information matrix. We establish the normal curvature diagnostics for the vector autoregressive model under three usual perturbation schemes for identifying possible influential observations. The effectiveness of the proposed diagnostics is examined by a simulation study, followed by our data analysis using the model to fit the weekly log returns of Chevron stock and the Standard \& Poor's 500 Index as an application.
{{\copyright} 2016 The Authors. Statistica Neerlandica {\copyright} 2016 VVS.}Spatial clustering of time series via mixture of autoregressions models and Markov random fieldshttps://zbmath.org/1528.620472024-03-13T18:33:02.981707Z"Nguyen, Hien D."https://zbmath.org/authors/?q=ai:nguyen.hien-duy"McLachlan, Geoffrey J."https://zbmath.org/authors/?q=ai:mclachlan.geoffrey-john"Ullmann, Jeremy F. P."https://zbmath.org/authors/?q=ai:ullmann.jeremy-f-p"Janke, Andrew L."https://zbmath.org/authors/?q=ai:janke.andrew-lSummary: Time series data arise in many medical and biological imaging scenarios. In such images, a time series is obtained at each of a large number of spatially dependent data units. It is interesting to organize these data into model-based clusters. A two-stage procedure is proposed. In stage 1, a mixture of autoregressions (MoAR) model is used to marginally cluster the data. The MoAR model is fitted using maximum marginal likelihood (MMaL) estimation via a minorization-maximization (MM) algorithm. In stage 2, a Markov random field (MRF) model induces a spatial structure onto the stage 1 clustering. The MRF model is fitted using maximum pseudolikelihood (MPL) estimation via an MM algorithm. Both the MMaL and MPL estimators are proved to be consistent. Numerical properties are established for both MM algorithms. A simulation study demonstrates the performance of the two-stage procedure. An application to the segmentation of a zebrafish brain calcium image is presented.
{{\copyright} 2016 The Authors. Statistica Neerlandica {\copyright} 2016 VVS.}Corrupted bifractal features in finite uncorrelated power-law distributed datahttps://zbmath.org/1528.620482024-03-13T18:33:02.981707Z"Olivares, Felipe"https://zbmath.org/authors/?q=ai:olivares.felipe"Zanin, Massimiliano"https://zbmath.org/authors/?q=ai:zanin.massimilianoSummary: Multifractal Detrended Fluctuation Analysis stands out as one of the most reliable methods for unveiling multifractal properties, specially when real-world time series are under analysis. However, little is known about how several aspects, like artefacts during the data acquisition process, affect its results. In this work we have numerically investigated the performance of Multifractal Detrended Fluctuation Analysis applied to synthetic finite uncorrelated data following a power-law distribution in the presence of additive noise, and periodic and randomly-placed outliers. We have found that, on one hand, spurious multifractality is observed as a result of data finiteness, while additive noise leads to an underestimation of the exponents \(h_q\) for \(q < 0\) even for low noise levels. On the other hand, additive periodic and randomly-located outliers result in a corrupted inverse multifractality around \(q = 0\). Moreover, the presence of randomly-placed outliers corrupts the entire multifractal spectrum, in a way proportional to their density. As an application, the multifractal properties of the time intervals between successive aircraft landings at three major European airports are investigated.Asymptotic analysis about the periodogram of a general class of time series models with spectral supportson lines not parallel to the main diagonalhttps://zbmath.org/1528.620492024-03-13T18:33:02.981707Z"Shi, Lei"https://zbmath.org/authors/?q=ai:shi.lei.5"Jain, Shilpi"https://zbmath.org/authors/?q=ai:jain.shilpi"Agarwal, Praveen"https://zbmath.org/authors/?q=ai:agarwal.praveen"Altayed, Yousif"https://zbmath.org/authors/?q=ai:altayed.yousif"Momani, Shaher"https://zbmath.org/authors/?q=ai:momani.shaher-mSummary: The aim of this paper is to make inference about a general class of time series models including fractional Brownian motion. The spectral of these processes is supported on lines not parallel to the diagonal \(T_1(x)=x\), \(T_j(x)= \alpha_jx\pm \beta_j,\) \(j=2,\dots,m\), in spectral square \([0,2\pi)\times[0,2\pi)\), and this class includes stationary, cyclostationary, almost cyclostationary time series and specially fractional Brownian motions. First, the periodogram of these processes is defined and auxiliary operator is applied to explore the distribution of the periodogram. Then the asymptotical estimation for the spectral density function is proposed and asymptotical Wishart function is found. Finally, the validity of the theoretical results is studied using simulated data sets.Should we condition on the number of points when modelling spatial point patterns?https://zbmath.org/1528.620502024-03-13T18:33:02.981707Z"Møller, Jesper"https://zbmath.org/authors/?q=ai:moller.jesper-michael|moller.jesper|moller.jesper-b"Vihrs, Ninna"https://zbmath.org/authors/?q=ai:vihrs.ninnaSummary: We discuss the practice of directly or indirectly assuming a model for the number of points when modelling spatial point patterns even though it is rarely possible to validate such a model in practice because most point pattern data consist of only one pattern. We therefore explore the possibility to condition on the number of points instead when fitting and validating spatial point process models. In a simulation study with different popular spatial point process models, we consider model validation using global envelope tests based on functional summary statistics. We find that conditioning on the number of points will for some functional summary statistics lead to more narrow envelopes and thus stronger tests and that it can also be useful for correcting for some conservativeness in the tests when testing composite hypothesis. However, for other functional summary statistics, it makes little or no difference to condition on the number of points. When estimating parameters in popular spatial point process models, we conclude that for mathematical and computational reasons, it is convenient to assume a distribution for the number of points.
{{\copyright} 2022 The Authors. International Statistical Review published by John Wiley \& Sons Ltd on behalf of International Statistical Institute.}A non-proportional hazards model with hazard ratio functions free from covariate valueshttps://zbmath.org/1528.620512024-03-13T18:33:02.981707Z"Kuk, Anthony Y. C."https://zbmath.org/authors/?q=ai:kuk.anthony-yung-cheungSummary: A brief survey on methods to handle non-proportional hazards in survival analysis is given with emphasis on short-term and long-term hazard ratio modelling. A drawback of the existing model of this nature is that except at time zero or infinity, the hazard ratio for a unit increase in the value of a covariate depends on the starting value. With two or more covariates, the hazard ratio for a unit increase in one covariate with other covariates held fixed depends in an unintended way on the values of the other covariates. We propose an alternative way to model short-term and long-term hazard ratios without the above drawbacks through a judicious choice of covariate-time interactions. Under the new model, it is easier to describe the time-varying effect of each covariate on the hazard. Nonparametric maximum likelihood estimation for the new model can be carried out in the same way as for the existing model. We also propose a product version of the existing model, which overcomes its second drawback but not the first. The advocated covariate-time interaction model provides a better fit to the Veterans Administration lung cancer data set than the original and product versions of the existing model.
{{\copyright} 2020 The Authors. International Statistical Review {\copyright} 2020 International Statistical Institute}Smooth estimation of a monotone hazard and a monotone density under random censoringhttps://zbmath.org/1528.620522024-03-13T18:33:02.981707Z"Lopuhaä, Hendrik P."https://zbmath.org/authors/?q=ai:lopuhaa.hendrik-p"Musta, Eni"https://zbmath.org/authors/?q=ai:musta.eniSummary: We consider kernel smoothed Grenander-type estimators for a monotone hazard rate and a monotone density in the presence of randomly right censored data. We show that they converge at rate \(n^{2/5}\) and that the limit distribution at a fixed point is Gaussian with explicitly given mean and variance. It is well known that standard kernel smoothing leads to inconsistency problems at the boundary points. It turns out that, also by using a boundary correction, we can only establish uniform consistency on intervals that stay away from the end point of the support (although we can go arbitrarily close to the right boundary).
{{\copyright} 2016 The Authors. Statistica Neerlandica {\copyright} 2016 VVS.}AI algorithms for fitting GARCH parameters to empirical financial datahttps://zbmath.org/1528.620532024-03-13T18:33:02.981707Z"De Clerk, Luke"https://zbmath.org/authors/?q=ai:clerk.luke-de"Savel'ev, Sergey"https://zbmath.org/authors/?q=ai:savelev.sergey-eSummary: We use Deep Artificial Neural Networks (ANNs) to estimate GARCH parameters for empirical financial time series. The algorithm we develop, allows us to fit autocovariance of squared returns of financial data, with certain time lags, the second order statistical moment, and the fourth order standardised moment. We have compared the time taken for the ANN algorithm to predict parameters for many time windows (around 4000), to that of the time taken for the Maximum Likelihood Estimation (MLE) methods of MatLabs's inbuilt statistical and econometric toolbox. The algorithm developed predicts all GARCH parameters in around 0.1 s, compared to the 11 seconds of the MLE method. Furthermore, we use a Model Confidence Set analysis to determine how accurate our parameter prediction algorithm is, when predicting volatility. The volatility prediction of different securities obtained employing the ANN has an error of around 25\%, compared to 40\% for the MLE methods.Poissonian two-armed bandit: a new approachhttps://zbmath.org/1528.620542024-03-13T18:33:02.981707Z"Kolnogorov, A. V."https://zbmath.org/authors/?q=ai:kolnogorov.alexander-vSummary: We consider a new approach to the continuous-time two-armed bandit problem in which incomes are described by Poisson processes. For this purpose, first, the control horizon is divided into equal consecutive half-intervals in which the strategy remains constant, and the incomes arrive in batches corresponding to these half-intervals. For finding the optimal piecewise constant Bayesian strategy and its corresponding Bayesian risk, a recursive difference equation is derived. The existence of a limiting value of the Bayesian risk when the number of half-intervals grows infinitely is established, and a partial differential equation for finding it is derived. Second, unlike previously considered settings of this problem, we analyze the strategy as a function of the current history of the controlled process rather than of the evolution of the posterior distribution. This removes the requirement of finiteness of the set of admissible parameters, which was imposed in previous settings. Simulation shows that in order to find the Bayesian and minimax strategies and risks in practice, it is sufficient to partition the arriving incomes into 30 batches. In the case of the minimax setting, it is shown that optimal processing of arriving incomes one by one is not more efficient than optimal batch processing if the control horizon grows infinitely.On the convergence of two types of estimators of quadratic variationhttps://zbmath.org/1528.620552024-03-13T18:33:02.981707Z"Yu, Xisheng"https://zbmath.org/authors/?q=ai:yu.xisheng(no abstract)Flexible \textit{cloglog} links for binomial regression models as an alternative for imbalanced medical datahttps://zbmath.org/1528.620562024-03-13T18:33:02.981707Z"Alves, Jessica S. B."https://zbmath.org/authors/?q=ai:alves.jessica-s-b"Bazán, Jorge L."https://zbmath.org/authors/?q=ai:bazan.jorge-luis"Arellano-Valle, Reinaldo B."https://zbmath.org/authors/?q=ai:arellano-valle.reinaldo-boris(no abstract)Bias-reduced estimators of conditional odds ratios in matched case-control studies with unmatched confoundinghttps://zbmath.org/1528.620572024-03-13T18:33:02.981707Z"Blagus, Rok"https://zbmath.org/authors/?q=ai:blagus.rok(no abstract)Fast approximations of pseudo-observations in the context of right censoring and interval censoringhttps://zbmath.org/1528.620582024-03-13T18:33:02.981707Z"Bouaziz, Olivier"https://zbmath.org/authors/?q=ai:bouaziz.olivier(no abstract)Three-period, two-treatment crossover design under long-term carryover effecthttps://zbmath.org/1528.620592024-03-13T18:33:02.981707Z"Chatterjee, Suryasish"https://zbmath.org/authors/?q=ai:chatterjee.suryasish"Bandyopadhyay, Uttam"https://zbmath.org/authors/?q=ai:bandyopadhyay.uttamSummary: The paper describes non-parametric approach for analysis of a three-period, two-treatment, four-sequence crossover design in which test procedure for interchangeability of the treatment effects is obtained. The proposed procedure is based on a non-parametric model, which incorporates, along with the direct treatment effects and the usual carryover effects, the long-term carryover effects. Relevant competitors are obtained. Related asymptotic results are given. By performing simulation study, we compared the procedures with respect to type I error rate and power. Furthermore, confidence intervals for treatment differences are studied. The procedures are illustrated with a data study.
{{\copyright} 2017 The Authors. Statistica Neerlandica {\copyright} 2017 VVS.}Synthesizing secondary data into survival analysis to improve estimation efficiencyhttps://zbmath.org/1528.620602024-03-13T18:33:02.981707Z"Chen, Chixiang"https://zbmath.org/authors/?q=ai:chen.chixiang"Yu, Tonghui"https://zbmath.org/authors/?q=ai:yu.tonghui"Shen, Biyi"https://zbmath.org/authors/?q=ai:shen.biyi"Wang, Ming"https://zbmath.org/authors/?q=ai:wang.ming.3(no abstract)Sample size calculation for the combination test under nonproportional hazardshttps://zbmath.org/1528.620612024-03-13T18:33:02.981707Z"Cheng, Huan"https://zbmath.org/authors/?q=ai:cheng.huan"He, Jianghua"https://zbmath.org/authors/?q=ai:he.jianghua(no abstract)Model-free conditional screening for ultrahigh-dimensional survival data via conditional distance correlationhttps://zbmath.org/1528.620622024-03-13T18:33:02.981707Z"Cui, Hengjian"https://zbmath.org/authors/?q=ai:cui.hengjian"Liu, Yanyan"https://zbmath.org/authors/?q=ai:liu.yanyan"Mao, Guangcai"https://zbmath.org/authors/?q=ai:mao.guangcai"Zhang, Jing"https://zbmath.org/authors/?q=ai:zhang.jing.12(no abstract)A classification model for continuous responses: identifying risk perception groups on health-related activitieshttps://zbmath.org/1528.620632024-03-13T18:33:02.981707Z"de Oliveira, Eduardo S. B."https://zbmath.org/authors/?q=ai:de-oliveira.eduardo-s-b"Wang, Xiaojing"https://zbmath.org/authors/?q=ai:wang.xiaojing"Bazán, Jorge L."https://zbmath.org/authors/?q=ai:bazan.jorge-luis(no abstract)Using mortality to predict incidence for rare and lethal cancers in very small areashttps://zbmath.org/1528.620642024-03-13T18:33:02.981707Z"Etxeberria, Jaione"https://zbmath.org/authors/?q=ai:etxeberria.jaione"Goicoa, Tomás"https://zbmath.org/authors/?q=ai:goicoa.tomas"Ugarte, Maria D."https://zbmath.org/authors/?q=ai:ugarte.maria-dolores(no abstract)Performance measures in dose-finding experimentshttps://zbmath.org/1528.620652024-03-13T18:33:02.981707Z"Flournoy, Nancy"https://zbmath.org/authors/?q=ai:flournoy.nancy"Moler, José"https://zbmath.org/authors/?q=ai:moler.jose-antonio"Plo, Fernando"https://zbmath.org/authors/?q=ai:plo.fernandoSummary: In the first phase of pharmaceutical development, and assuming that the probability of positive response increases with dose, the main statistical goal is to estimate a percentile of the dose-response function for a given target value \(\Gamma\). We compare the Maximum Likelihood and centred isotonic regression estimators of the target dose and we discuss several performance criteria to assess inferential precision, the amount of toxicity exposure and the trade-off between them for a set of some exemplary adaptive designs. We compare these designs using graphical tools. Several scenarios are considered using simulation, including the use of several start-up rules, the change of slope of the dose-toxicity function at the target dose and also different theoretical models, as logistic, normal or skew-normal distribution functions.
{{\copyright} 2020 The Authors. International Statistical Review published by John Wiley \& Sons Ltd on behalf of International Statistical Institute.}Challenges in interpreting epidemiological surveillance data -- experiences from Germanyhttps://zbmath.org/1528.620662024-03-13T18:33:02.981707Z"Fritz, Cornelius"https://zbmath.org/authors/?q=ai:fritz.cornelius"De Nicola, Giacomo"https://zbmath.org/authors/?q=ai:de-nicola.giacomo"Günther, Felix"https://zbmath.org/authors/?q=ai:gunther.felix.1|gunther.felix"Rügamer, David"https://zbmath.org/authors/?q=ai:rugamer.david"Rave, Martje"https://zbmath.org/authors/?q=ai:rave.martje"Schneble, Marc"https://zbmath.org/authors/?q=ai:schneble.marc"Bender, Andreas"https://zbmath.org/authors/?q=ai:bender.andreas-o"Weigert, Maximilian"https://zbmath.org/authors/?q=ai:weigert.maximilian"Brinks, Ralph"https://zbmath.org/authors/?q=ai:brinks.ralph"Hoyer, Annika"https://zbmath.org/authors/?q=ai:hoyer.annika"Berger, Ursula"https://zbmath.org/authors/?q=ai:berger.ursula"Küchenhoff, Helmut"https://zbmath.org/authors/?q=ai:kuchenhoff.helmut"Kauermann, Göran"https://zbmath.org/authors/?q=ai:kauermann.goran(no abstract)Correcting for heterogeneity and non-comparability bias in multicenter clinical trials with a rescaled random-effect excess hazard modelhttps://zbmath.org/1528.620672024-03-13T18:33:02.981707Z"Goungounga, Juste A."https://zbmath.org/authors/?q=ai:goungounga.juste-a"Grafféo, Nathalie"https://zbmath.org/authors/?q=ai:graffeo.nathalie"Charvat, Hadrien"https://zbmath.org/authors/?q=ai:charvat.hadrien"Giorgi, Roch"https://zbmath.org/authors/?q=ai:giorgi.roch(no abstract)Bayesian and influence function-based empirical likelihoods for inference of sensitivity to the early diseased stage in diagnostic testshttps://zbmath.org/1528.620682024-03-13T18:33:02.981707Z"Hai, Yan"https://zbmath.org/authors/?q=ai:hai.yan"Shi, Shuangfei"https://zbmath.org/authors/?q=ai:shi.shuangfei"Qin, Gengsheng"https://zbmath.org/authors/?q=ai:qin.gengsheng(no abstract)Random-effects meta-analysis models for the odds ratio in the case of rare events under different data-generating models: a simulation studyhttps://zbmath.org/1528.620692024-03-13T18:33:02.981707Z"Jansen, Katrin"https://zbmath.org/authors/?q=ai:jansen.katrin"Holling, Heinz"https://zbmath.org/authors/?q=ai:holling.heinz(no abstract)Rectangular tolerance regions and multivariate normal reference regions in laboratory medicinehttps://zbmath.org/1528.620702024-03-13T18:33:02.981707Z"Lucagbo, Michael Daniel"https://zbmath.org/authors/?q=ai:lucagbo.michael-daniel"Mathew, Thomas"https://zbmath.org/authors/?q=ai:mathew.thomas(no abstract)Stratified modestly weighted log-rank tests in settings with an anticipated delayed separation of survival curveshttps://zbmath.org/1528.620712024-03-13T18:33:02.981707Z"Magirr, Dominic"https://zbmath.org/authors/?q=ai:magirr.dominic"Jiménez, José L."https://zbmath.org/authors/?q=ai:jimenez.jose-luis-carmona|jimenez.jose-l(no abstract)Expected life years compared to the general populationhttps://zbmath.org/1528.620722024-03-13T18:33:02.981707Z"Manevski, Damjan"https://zbmath.org/authors/?q=ai:manevski.damjan"Ružić Gorenjec, Nina"https://zbmath.org/authors/?q=ai:ruzic-gorenjec.nina"Andersen, Per Kragh"https://zbmath.org/authors/?q=ai:andersen.per-kragh"Pohar Perme, Maja"https://zbmath.org/authors/?q=ai:pohar-perme.maja(no abstract)A latent class model to multiply impute missing treatment indicators in observational studies when inferences of the treatment effect are made using propensity score matchinghttps://zbmath.org/1528.620732024-03-13T18:33:02.981707Z"Mitra, Robin"https://zbmath.org/authors/?q=ai:mitra.robin.1|mitra.robin(no abstract)Some new results on Cox-Czanner divergence and their applications in survival studieshttps://zbmath.org/1528.620742024-03-13T18:33:02.981707Z"Nair, N. Unnikrishnan"https://zbmath.org/authors/?q=ai:nair.n-unnikrishnan"Subhash, Silpa"https://zbmath.org/authors/?q=ai:subhash.silpa"Sunoj, S. M."https://zbmath.org/authors/?q=ai:sunoj.sreenarayanapurath-madhavan(no abstract)Dealing with separation or near-to-separation in the model for multinomial response with application to childhood health seeking behavior data from a complex surveyhttps://zbmath.org/1528.620752024-03-13T18:33:02.981707Z"Nusrat, Nowrin"https://zbmath.org/authors/?q=ai:nusrat.nowrin"Rahman, M. S."https://zbmath.org/authors/?q=ai:rahman.m-shafiqurSummary: Separation or monotone-likelihood can be observed in fitting process of a multinomial logistic model using maximum likelihood estimation (MLE) when sample size is small and/or one of the outcome categories is rare and/or there is one or more influential covariates, resulting in infinite or biased estimate of at least one regression coefficient of the model. This study investigated empirically to identify the optimal data condition to define both `separation' and `near-to-separation' (partial separation) and explored their consequences in MLE and provided a solution by applying a penalized likelihood approach, which has been proposed in the literature, by adding a Jeffreys prior-based penalty term to the original likelihood function to remove the first-order bias in the MLEs of the multinomial logit model via equivalent Poisson regression. Furthermore, the penalized estimating equation (PMLE) is extended to a weighted estimating equation allowing for survey-weight for analyzing data from a complex survey. The simulation study suggests that the PMLE outperforms the MLE by providing smaller amount of bias and mean squared of error and better coverage. The methods are applied to analyze data on choice of health facility for treatment of childhood diseases.Lessons from West Virginia's pandemic responsehttps://zbmath.org/1528.620762024-03-13T18:33:02.981707Z"Price, Bradley S."https://zbmath.org/authors/?q=ai:price.bradley-s"Saldanha, John P."https://zbmath.org/authors/?q=ai:saldanha.john-p"Drake, Dariane"https://zbmath.org/authors/?q=ai:drake.dariane"Kopp, Katherine"https://zbmath.org/authors/?q=ai:kopp.katherine(no abstract)Bayesian estimation of two-part joint models for a longitudinal semicontinuous biomarker and a terminal event with INLA: interests for cancer clinical trial evaluationhttps://zbmath.org/1528.620772024-03-13T18:33:02.981707Z"Rustand, Denis"https://zbmath.org/authors/?q=ai:rustand.denis"van Niekerk, Janet"https://zbmath.org/authors/?q=ai:van-niekerk.janet"Rue, Håvard"https://zbmath.org/authors/?q=ai:rue.havard"Tournigand, Christophe"https://zbmath.org/authors/?q=ai:tournigand.christophe"Rondeau, Virginie"https://zbmath.org/authors/?q=ai:rondeau.virginie"Briollais, Laurent"https://zbmath.org/authors/?q=ai:briollais.laurent(no abstract)Bayesian design for minimizing prediction uncertainty in bivariate spatial responses with applications to air quality monitoringhttps://zbmath.org/1528.620782024-03-13T18:33:02.981707Z"Senarathne, S. G. J."https://zbmath.org/authors/?q=ai:senarathne.s-g-j"Müller, Werner G."https://zbmath.org/authors/?q=ai:muller.werner-g"McGree, James M."https://zbmath.org/authors/?q=ai:mcgree.james-m(no abstract)Spatial correlated incidence modeling with zero inflationhttps://zbmath.org/1528.620792024-03-13T18:33:02.981707Z"Wang, Feifei"https://zbmath.org/authors/?q=ai:wang.feifei"Li, Haofeng"https://zbmath.org/authors/?q=ai:li.haofeng"Wang, Han"https://zbmath.org/authors/?q=ai:wang.han"Li, Yang"https://zbmath.org/authors/?q=ai:li.yang.49|li.yang.50|li.yang.7|li.yang.9|li.yang.8|li.yang.2|li.yang.6|li.yang.11|li.yang.44|li.yang.47|li.yang|li.yang.48|li.yang.17|li.yang.28|yang.li.2|li.yang.40|li.yang.4|li.yang.12|li.yang.13|li.yang.45|li.yang.5|li.yang.55(no abstract)Estimation of conditional average treatment effect by covariates balance methodshttps://zbmath.org/1528.620802024-03-13T18:33:02.981707Z"Wang, Jun"https://zbmath.org/authors/?q=ai:wang.jun.79"Liu, Changbiao"https://zbmath.org/authors/?q=ai:liu.changbiaoSummary: Conditional average treatment effects estimation is one of the crucial mainstays in observational studies. The conditional average treatment effect is defined as a functional parameter which is used to describe the variation of average treatment effect condition on some covariates. Based on the unconfoundedness assumption, we propose the covariates balance method to estimate the propensity score, and the estimated propensity score is applied to the non-parametric method to estimate the conditional average treatment effect. The proposed method is robust and superior to the parametric approach. The proposed method has a smaller RMSE than the true method when the propensity score model is correct specified. Meanwhile, compared with the kernel method, the proposed method is much more computationally efficient. The proposed estimator is consistent and asymptotic under some regularity conditions. Finally, we apply the proposed method to estimate the effect of maternal smoking on low birth weight infants given the age of mothers.Improving sandwich variance estimation for marginal Cox analysis of cluster randomized trialshttps://zbmath.org/1528.620812024-03-13T18:33:02.981707Z"Wang, Xueqi"https://zbmath.org/authors/?q=ai:wang.xueqi.1|wang.xueqi"Turner, Elizabeth L."https://zbmath.org/authors/?q=ai:turner.elizabeth-l"Li, Fan"https://zbmath.org/authors/?q=ai:li.fan(no abstract)Incorporating infectious duration-dependent transmission into Bayesian epidemic modelshttps://zbmath.org/1528.620822024-03-13T18:33:02.981707Z"Ward, Caitlin"https://zbmath.org/authors/?q=ai:ward.caitlin"Brown, Grant D."https://zbmath.org/authors/?q=ai:brown.grant-d"Oleson, Jacob J."https://zbmath.org/authors/?q=ai:oleson.jacob-j(no abstract)Analyzing recurrent and nonrecurrent terminal events data in discrete timehttps://zbmath.org/1528.620832024-03-13T18:33:02.981707Z"Wen, Chi-Chung"https://zbmath.org/authors/?q=ai:wen.chi-chung"Chen, Yi-Hau"https://zbmath.org/authors/?q=ai:chen.yihau(no abstract)Conditional assessment of the impact of a Hausman pretest on confidence intervalshttps://zbmath.org/1528.620842024-03-13T18:33:02.981707Z"Kabaila, Paul"https://zbmath.org/authors/?q=ai:kabaila.paul-v"Mainzer, Rheanna"https://zbmath.org/authors/?q=ai:mainzer.rheanna"Farchione, Davide"https://zbmath.org/authors/?q=ai:farchione.davideSummary: In the analysis of clustered and longitudinal data, which includes a covariate that varies both between and within clusters, a Hausman pretest is commonly used to decide whether subsequent inference is made using the linear random intercept model or the fixed effects model. We assess the effect of this pretest on the coverage probability and expected length of a confidence interval for the slope, conditional on the observed values of the covariate. This assessment has the advantages that it (i) relates to the values of this covariate at hand, (ii) is valid irrespective of how this covariate is generated, (iii) uses exact finite sample results, and (iv) results in an assessment that is determined by the values of this covariate and only two unknown parameters. For two real data sets, our conditional analysis shows that the confidence interval constructed after a Hausman pretest should not be used.
{{\copyright} 2017 The Authors. Statistica Neerlandica {\copyright} 2017 VVS.}Unification of some multivariate process capability indices for asymmetric specification regionhttps://zbmath.org/1528.620852024-03-13T18:33:02.981707Z"Chatterjee, Moutushi"https://zbmath.org/authors/?q=ai:chatterjee.moutushi"Chakraborty, Ashis Kumar"https://zbmath.org/authors/?q=ai:chakraborty.ashis-kumarSummary: In manufacturing industries, it is often seen that the bilateral specification limits corresponding to a particular quality characteristic are not symmetric with respect to the stipulated target. A unified superstructure \(C_p^{\prime\prime}(u, v)\) of univariate process capability indices was specially designed for processes with asymmetric specification limits. However, as in most of the practical situations a process consists of a number of inter-related quality characteristics, subsequently, a multivariate analogue of \(C_p^{\prime\prime}(u, v)\), which is called \(C_M(u, v)\), was developed. In the present paper, we study some properties of \(C_M(u, v)\) like threshold value and compatibility with the asymmetry in loss function. We also discuss estimation procedures for plug-in estimators of some of the member indices of \(C_M(u, v)\). Finally, the superstructure is applied to a numerical example to supplement the theory developed in this article.
{{\copyright} 2017 The Authors. Statistica Neerlandica {\copyright} 2017 VVS.}Regional differences of high-quality development level for manufacturing industry in Chinahttps://zbmath.org/1528.620862024-03-13T18:33:02.981707Z"Han, Zhi-Ying"https://zbmath.org/authors/?q=ai:han.zhi-ying"Liu, Yong"https://zbmath.org/authors/?q=ai:liu.yong.15"Guo, Xue-ge"https://zbmath.org/authors/?q=ai:guo.xue-ge"Xu, Jun-qian"https://zbmath.org/authors/?q=ai:xu.jun-qianSummary: The development of China's manufacturing industry is still facing the challenge of regional imbalance. To solve the problem of development imbalance, it is necessary to realize regional development. First, we must analyze the development characteristics of different regions. To this end, we consider the requirements of the new development era and design an evaluation index system for the high-quality development level of the manufacturing industry from the dimensions of innovation, green, and efficiency. Then construct a novel hybrid model which combines the grey incidence clustering model and AP algorithm for panel data in this paper. According to the statistical data from 2014 to 2018, we find out the high-quality development of China's manufacturing industry is characterized by obvious regional differences, different development stages and different constraints.Cusums for tracking arbitrary functionalshttps://zbmath.org/1528.620872024-03-13T18:33:02.981707Z"Withers, Christopher S."https://zbmath.org/authors/?q=ai:withers.christopher-s"Nadarajah, Saralees"https://zbmath.org/authors/?q=ai:nadarajah.saraleesSummary: Cusum charts are widely used for detecting deviations of a process about a target value and also for finding evidence of change in the mean of a process. The testing theory approximates the process by a Wiener process or a Brownian bridge, respectively. For quality control, it is important that other aspects are monitored in addition to or instead of the mean. Here, we show that cusum theory is easily adapted when the target is not the mean but some other aspect of the distribution.
{{\copyright} 2016 The Authors. Statistica Neerlandica {\copyright} 2016 VVS.}Sparse regression for data-driven deterrence functions in gravity modelshttps://zbmath.org/1528.620882024-03-13T18:33:02.981707Z"Rubio-Herrero, Javier"https://zbmath.org/authors/?q=ai:rubio-herrero.javier"Muñuzuri, Jesús"https://zbmath.org/authors/?q=ai:munuzuri.jesusSummary: Gravity models have been one of the mathematical models of choice for trip distribution modeling efforts during many decades. Their simplicity offset their drawbacks, as they usually provide a reasonably good rationale for how goods are distributed in a transportation network with relatively little information. These gravity models, however, rely on the definition of a deterrence function that acts as a counterweight of the levels of supply and demand. This function is usually picked from a series of off-the-shelf available functions that only depend on a handful of parameters that need to be calibrated. Because of the limited off-the shelf options, gravity models lack flexibility in some occasions. In this paper, we tackle the use of sparse regression techniques that can accommodate data more flexibly with a reduced number of terms. Using interregional freight origin-destination data from Spain, we test two alternatives, namely, best subset regression and lasso regression. We show that the first one performs better in finding parsimonious deterrence functions and we attain gravity models that fit the data up to 14.5\% better than classical deterrence functions.Bayesian approach to LR assessment in case of rare type matchhttps://zbmath.org/1528.620892024-03-13T18:33:02.981707Z"Cereda, Giulia"https://zbmath.org/authors/?q=ai:cereda.giuliaSummary: The likelihood ratio (LR) is largely used to evaluate the relative weight of forensic data regarding two hypotheses, and for its assessment, Bayesian methods are widespread in the forensic field. However, the Bayesian `recipe' for the LR presented in most of the literature consists of plugging-in Bayesian estimates of the involved nuisance parameters into a frequentist-defined LR: frequentist and Bayesian methods are thus mixed, giving rise to solutions obtained by hybrid reasoning. This paper provides the derivation of a proper Bayesian approach to assess LRs for the `rare type match problem', the situation in which the expert wants to evaluate a match between the DNA profile of a suspect and that of a trace from the crime scene, and this profile has never been observed before in the database of reference. LR assessment using the two most popular Bayesian models (beta-binomial and Dirichlet-multinomial) is discussed and compared with corresponding plug-in versions.
{{\copyright} 2017 The Author. Statistica Neerlandica {\copyright} 2017 VVS.}An application of the generalized Poisson difference distribution to the Bayesian modelling of football scoreshttps://zbmath.org/1528.620902024-03-13T18:33:02.981707Z"Shahtahmassebi, Golnaz"https://zbmath.org/authors/?q=ai:shahtahmassebi.golnaz"Moyeed, Rana"https://zbmath.org/authors/?q=ai:moyeed.rana-aSummary: The analysis of sports data, in particular football match outcomes, has always produced an immense interest among the statisticians. In this paper, we adopt the generalized Poisson difference distribution (GPDD) to model the goal difference of football matches. We discuss the advantages of the proposed model over the Poisson difference (PD) model, which was also used for the same purpose. The GPDD model, like the PD model, is based on the goal difference in each game that allows us to account for the correlation without explicitly modelling it. The main advantage of the GPDD model is its flexibility in the tails by considering shorter as well as longer tails than the PD distribution. We carry out the analysis in a Bayesian framework in order to incorporate external information, such as historical knowledge or data, through the prior distributions. We model both the mean and the variance of the goal difference and show that such a model performs considerably better than a model with a fixed variance. Finally, the proposed model is fitted to the 2012--2013 Italian Serie A football data, and various model diagnostics are carried out to evaluate the performance of the model.
{{\copyright} 2016 The Authors. Statistica Neerlandica {\copyright} 2016 VVS.}Tests of normality of functional datahttps://zbmath.org/1528.620912024-03-13T18:33:02.981707Z"Górecki, Tomasz"https://zbmath.org/authors/?q=ai:gorecki.tomasz-t"Horváth, Lajos"https://zbmath.org/authors/?q=ai:horvath.lajos"Kokoszka, Piotr"https://zbmath.org/authors/?q=ai:kokoszka.piotr-sSummary: The paper is concerned with testing normality in samples of curves and error curves estimated from functional regression models. We propose a general paradigm based on the application of multivariate normality tests to vectors of functional principal components scores. We examine finite sample performance of a number of such tests and select the best performing tests. We apply them to several extensively used functional data sets and determine which can be treated as normal, possibly after a suitable transformation. We also offer practical guidance on software implementations of all tests we study and develop large sample justification for tests based on sample skewness and kurtosis of functional principal component scores.
{{\copyright} 2020 The Authors. International Statistical Review {\copyright} 2020 International Statistical Institute}Random sampling high dimensional model representation Gaussian process regression (RS-HDMR-GPR) for representing multidimensional functions with machine-learned lower-dimensional terms allowing insight with a general methodhttps://zbmath.org/1528.650122024-03-13T18:33:02.981707Z"Ren, Owen"https://zbmath.org/authors/?q=ai:ren.owen"Boussaidi, Mohamed Ali"https://zbmath.org/authors/?q=ai:boussaidi.mohamed-ali"Voytsekhovsky, Dmitry"https://zbmath.org/authors/?q=ai:voytsekhovsky.dmitry"Ihara, Manabu"https://zbmath.org/authors/?q=ai:ihara.manabu"Manzhos, Sergei"https://zbmath.org/authors/?q=ai:manzhos.sergeiSummary: We present an implementation for the RS-HDMR-GPR (Random Sampling High Dimensional Model Representation Gaussian Process Regression) method. The method builds representations of multivariate functions with lower-dimensional terms, either as an expansion over orders of coupling or using terms of only a given dimensionality. This facilitates, in particular, recovering functional dependence from sparse data. The method also allows for imputation of missing values of the variables and for a significant pruning of the useful number of HDMR terms. It can also be used for estimating relative importance of different combinations of input variables, thereby adding an element of insight to a general machine learning method, in a way that can be viewed as extending the automatic relevance determination approach. The capabilities of the method and of the associated Python software tool are demonstrated on test cases involving synthetic analytic functions, the potential energy surface of the water molecule, kinetic energy densities of materials (crystalline magnesium, aluminum, and silicon), and financial market data.Fast and accurate Gaussian kernel ridge regression using matrix decompositions for preconditioninghttps://zbmath.org/1528.650192024-03-13T18:33:02.981707Z"Shabat, Gil"https://zbmath.org/authors/?q=ai:shabat.gil"Choshen, Era"https://zbmath.org/authors/?q=ai:choshen.era"Ben Or, Dvir"https://zbmath.org/authors/?q=ai:or.dvir-ben"Carmel, Nadav"https://zbmath.org/authors/?q=ai:carmel.nadavSummary: This paper presents a preconditioner-based method for solving a kernel ridge regression problem. In contrast to other methods, which utilize either fast matrix-vector multiplication or a preconditioner, the suggested approach uses randomized matrix decompositions for building a preconditioner with a special structure that can also utilize fast matrix-vector multiplications. This hybrid approach is efficient in reducing the condition number, exact, and computationally efficient, enabling the processing of large datasets with computational complexity linear to the number of data points. Also, a theoretical upper bound for the condition number is provided. For Gaussian kernels, we show that given a desired condition number, the rank of the needed preconditioner can be determined directly from the dataset.Low-rank matrix estimation from rank-one projections by unlifted convex optimizationhttps://zbmath.org/1528.650252024-03-13T18:33:02.981707Z"Bahmani, Sohail"https://zbmath.org/authors/?q=ai:bahmani.sohail"Lee, Kiryung"https://zbmath.org/authors/?q=ai:lee.kiryungSummary: We study an estimator with a convex formulation for recovery of low-rank matrices from rank-one projections. Using initial estimates of the factors of the target \(d_1\times d_2\) matrix of rank-\(r\), the estimator admits a practical subgradient method operating in a space of dimension \(r(d_1+d_2)\). This property makes the estimator significantly more scalable than the convex estimators based on lifting and semidefinite programming. Furthermore, we present a streamlined analysis for exact recovery under the real Gaussian measurement model, as well as the partially derandomized measurement model by using the spherical \(t\)-design. We show that under both models the estimator succeeds, with high probability, if the number of measurements exceeds \(r^2 (d_1+d_2)\) up to some logarithmic factors. This sample complexity improves on the existing results for nonconvex iterative algorithms.DAFI: an open-source framework for ensemble-based data assimilation and field inversionhttps://zbmath.org/1528.650642024-03-13T18:33:02.981707Z"Michelén Ströfer, Carlos A."https://zbmath.org/authors/?q=ai:michelen-strofer.carlos-a"Zhang, Xin-Lei"https://zbmath.org/authors/?q=ai:zhang.xinlei"Xiao, Heng"https://zbmath.org/authors/?q=ai:xiao.hengSummary: In many areas of science and engineering, it is a common task to infer physical fields from sparse observations. This paper presents the DAFI code intended as a flexible framework for two broad classes of such inverse problems: data assimilation and field inversion. DAFI generalizes these diverse problems into a general formulation and solves it with ensemble Kalman filters, a family of ensemble-based, derivative-free, Bayesian methods. This Bayesian approach has the added advantage of providing built-in uncertainty quantification. Moreover, the code provides tools for performing common tasks related to random fields, as well as I/O utilities for integration with the open-source finite volume tool OpenFOAM. The code capabilities are showcased through several test cases including state and parameter estimation for the Lorenz dynamic system, field inversion for the diffusion equations, and uncertainty quantification. The object-oriented nature of the code allows for easily interchanging different solution methods and different physics problems. It provides a simple interface for the users to supply their domain-specific physics models. Finally, the code can be used as a test-bed for new ensemble-based data assimilation and field inversion methods.Parameter identification in uncertain scalar conservation laws discretized with the discontinuous stochastic Galerkin schemehttps://zbmath.org/1528.650822024-03-13T18:33:02.981707Z"Schlachter, Louisa"https://zbmath.org/authors/?q=ai:schlachter.louisa"Totzeck, Claudia"https://zbmath.org/authors/?q=ai:totzeck.claudiaSummary: We study an identification problem which estimates the parameters of the underlying random distribution for uncertain scalar conservation laws. The hyperbolic equations are discretized with the so-called discontinuous stochastic Galerkin method, i.e., using a spatial discontinuous Galerkin scheme and a Multielement stochastic Galerkin ansatz in the random space. We assume an uncertain flux or uncertain initial conditions and that a data set of an observed solution is given. The uncertainty is assumed to be uniformly distributed on an unknown interval and we focus on identifying the correct endpoints of this interval. The first-order optimality conditions from the discontinuous stochastic Galerkin discretization are computed on the time-continuous level. Then, we solve the resulting semi-discrete forward and backward schemes with the Runge-Kutta method. To illustrate the feasibility of the approach, we apply the method to a stochastic advection and a stochastic equation of Burgers' type. The results show that the method is able to identify the distribution parameters of the random variable in the uncertain differential equation even if discontinuities are present.DL-PDE: deep-learning based data-driven discovery of partial differential equations from discrete and noisy datahttps://zbmath.org/1528.650932024-03-13T18:33:02.981707Z"Xu, Hao"https://zbmath.org/authors/?q=ai:xu.hao.5"Chang, Haibin"https://zbmath.org/authors/?q=ai:chang.haibin"Zhang, Dongxiao"https://zbmath.org/authors/?q=ai:zhang.dongxiaoSummary: In recent years, data-driven methods have been developed to learn dynamical systems and partial differential equations (PDE). The goal of such work is to discover unknown physics and corresponding equations. However, prior to achieving this goal, major challenges remain to be resolved, including learning PDE under noisy data and limited discrete data. To overcome these challenges, in this work, a deep-learning based data-driven method, called DL-PDE, is developed to discover the governing PDEs of underlying physical processes. The DL-PDE method combines deep learning via neural networks and data-driven discovery of PDE via sparse regressions. In the DL-PDE, a neural network is first trained, then a large amount of meta-data is generated, and the required derivatives are calculated by automatic differentiation. Finally, the form of PDE is discovered by sparse regression. The proposed method is tested with physical processes, governed by the diffusion equation, the convection-diffusion equation, the Burgers equation, and the Korteweg-de Vries (KdV) equation, for proof-of-concept and applications in real-world engineering settings. The proposed method achieves satisfactory results when data are noisy and limited.Machine learning for science: mathematics at the interface of data-driven and mechanistic modelling. Abstracts from the workshop held June 11--16, 2023https://zbmath.org/1528.680322024-03-13T18:33:02.981707ZSummary: Rapid progress in machine learning is enabling scientific advances across a range of disciplines. However, the utility of machine learning for science remains constrained by its current inability to translate insights from data about the dynamics of a system to new scientific knowledge about why those dynamics emerge, as traditionally represented by physical modelling. Mathematics is the interface that bridges data-driven and physical models of the world and can provide a foundation for delivering such knowledge. This workshop convened researchers working across domains with a shared interest in mathematics, machine learning, and their application in the sciences, to explore how tools of mathematics can help build machine learning tools for scientific discovery.Modules in Robinson spaceshttps://zbmath.org/1528.682602024-03-13T18:33:02.981707Z"Carmona, Mikhael"https://zbmath.org/authors/?q=ai:carmona.mikhael"Chepoi, Victor"https://zbmath.org/authors/?q=ai:chepoi.victor-d"Naves, Guyslain"https://zbmath.org/authors/?q=ai:naves.guyslain"Préa, Pascal"https://zbmath.org/authors/?q=ai:prea.pascalSummary: A \textit{Robinson space} is a dissimilarity space \((X,d)\) (i.e., a set \(X\) of size \(n\) and a dissimilarity \(d\) on \(X)\) for which there exists a total order \(<\) on \(X\) such that \(x<y<z\) implies that \(d(x,z)\geq\max\{d(x,y), d(y,z)\}\). Recognizing if a dissimilarity space is Robinson has numerous applications in seriation and classification. An \textit{mmodule} of \((X,d)\) (generalizing the notion of a module in graph theory) is a subset \(M\) of \(X\) which is not distinguishable from the outside of \(M\); i.e., the distance from any point of \(X\setminus M\) to all points of \(M\) is the same. If \(p\) is any point of \(X\), then \(\{p\}\), and the maximal-by-inclusion mmodules of \((X,d)\) not containing \(p\) define a partition of \(X\), called the \textit{copoint partition.} In this paper, we investigate the structure of mmodules in Robinson spaces and use it and the copoint partition to design a simple and practical divide-and-conquer algorithm for recognition of Robinson spaces in optimal \(O(n^2)\) time.A combinatorial multi-armed bandit approach to correlation clusteringhttps://zbmath.org/1528.683402024-03-13T18:33:02.981707Z"Gullo, F."https://zbmath.org/authors/?q=ai:gullo.francesco"Mandaglio, D."https://zbmath.org/authors/?q=ai:mandaglio.d"Tagarelli, A."https://zbmath.org/authors/?q=ai:tagarelli.andreaSummary: Given a graph whose edges are assigned positive-type and negative-type weights, the problem of \textit{correlation clustering} aims at grouping the graph vertices so as to minimize (resp. maximize) the sum of negative-type (resp. positive-type) intra-cluster weights plus the sum of positive-type (resp. negative-type) inter-cluster weights. In correlation clustering, it is typically assumed that the weights are readily available. This is a rather strong hypothesis, which is unrealistic in several scenarios. To overcome this limitation, in this work we focus on the setting where edge weights of a correlation-clustering instance are unknown, and they have to be estimated in multiple rounds, while performing the clustering. The clustering solutions produced in the various rounds provide a feedback to properly adjust the weight estimates, and the goal is to maximize the cumulative quality of the clusterings. We tackle this problem by resorting to the reinforcement-learning paradigm, and, specifically, we design for the first time a Combinatorial Multi-Armed Bandit (CMAB) framework for correlation clustering. We provide a variety of contributions, namely (1) formulations of the minimization and maximization variants of correlation clustering in a CMAB setting; (2) adaptation of well-established CMAB algorithms to the correlation-clustering context; (3) regret analyses to theoretically bound the accuracy of these algorithms; (4) design of further (heuristic) algorithms to have the probability constraint satisfied at every round (key condition to soundly adopt efficient yet effective algorithms for correlation clustering as CMAB oracles); (5) extensive experimental comparison among a variety of both CMAB and non-CMAB approaches for correlation clustering.Optimal learning with anisotropic Gaussian SVMshttps://zbmath.org/1528.683422024-03-13T18:33:02.981707Z"Hang, Hanyuan"https://zbmath.org/authors/?q=ai:hang.hanyuan"Steinwart, Ingo"https://zbmath.org/authors/?q=ai:steinwart.ingoSummary: This paper investigates the nonparametric regression problem using SVMs with anisotropic Gaussian RBF kernels. Under the assumption that the target functions are resided in certain anisotropic Besov spaces, we establish the almost optimal learning rates, more precisely, optimal up to some logarithmic factor, presented by the effective smoothness. By taking the effective smoothness into consideration, our almost optimal learning rates are faster than those obtained with the underlying RKHSs being certain anisotropic Sobolev spaces. Moreover, if the target function depends only on fewer dimensions, faster learning rates can be further achieved.Robust pairwise learning with Huber losshttps://zbmath.org/1528.683442024-03-13T18:33:02.981707Z"Huang, Shouyou"https://zbmath.org/authors/?q=ai:huang.shouyou"Wu, Qiang"https://zbmath.org/authors/?q=ai:wu.qiangSummary: Pairwise learning naturally arises from machine learning tasks such as AUC maximization, ranking, and metric learning. In this paper we propose a new pairwise learning algorithm based on the additive noise regression model, which adopts the pairwise Huber loss and applies effectively even to the situation where the noise only satisfies a weak moment condition. Owing to the robustness of Huber loss function, this new method is resistant to heavy-tailed errors or outliers in the response variable. We establish a comparison theorem to characterize the gap between the excess generalization error and the prediction error. We derive the error bounds and convergence rates under appropriate conditions. It is worth mentioning that all the results are established under the \((1+\epsilon)\)-th moment condition of the noise variable. It is rather weak particularly in the case of \(\epsilon<1\), which means the noise variable does not even admit a finite variance.Optimal rates of distributed regression with imperfect kernelshttps://zbmath.org/1528.683482024-03-13T18:33:02.981707Z"Sun, Hongwei"https://zbmath.org/authors/?q=ai:sun.hongwei"Wu, Qiang"https://zbmath.org/authors/?q=ai:wu.qiangSummary: Distributed machine learning systems have been receiving increasing attentions for their efficiency to process large scale data. Many distributed frameworks have been proposed for different machine learning tasks. In this paper, we study the distributed kernel regression via the divide and conquer approach. The learning process consists of three stages. Firstly, the data is partitioned into multiple subsets. Then a base kernel regression algorithm is applied to each subset to learn a local regression model. Finally the local models are averaged to generate the final regression model for the purpose of predictive analytics or statistical inference. This approach has been proved asymptotically minimax optimal if the kernel is perfectly selected so that the true regression function lies in the associated reproducing kernel Hilbert space. However, this is usually, if not always, impractical because kernels that can only be selected via prior knowledge or a tuning process are hardly perfect. Instead it is more common that the kernel is good enough but imperfect in the sense that the true regression can be well approximated by but does not lie exactly in the kernel space. We show distributed kernel regression can still achieve capacity independent optimal rate in this case. To this end, we first establish a general framework that allows to analyze distributed regression with response weighted base algorithms by bounding the error of such algorithms on a single data set, provided that the error bounds have factored the impact of unexplained variance of the response variable. Then we perform a leave one out analysis of the kernel ridge regression and bias corrected kernel ridge regression, which in combination with the aforementioned framework allows us to derive sharp error bounds and capacity independent optimal rates for the associated distributed kernel regression algorithms. As a byproduct of the thorough analysis, we also prove the kernel ridge regression can achieve rates faster than \(O(N^{-1})\) (where \(N\) is the sample size) in the noise free setting which, to our best knowledge, are first observed and novel in regression learning.Deep kernel supervised hashing for node classification in structural networkshttps://zbmath.org/1528.683552024-03-13T18:33:02.981707Z"Guo, Jia-Nan"https://zbmath.org/authors/?q=ai:guo.jia-nan"Mao, Xian-Ling"https://zbmath.org/authors/?q=ai:mao.xian-ling"Lin, Shu-Yang"https://zbmath.org/authors/?q=ai:lin.shu-yang"Wei, Wei"https://zbmath.org/authors/?q=ai:wei.wei.3|wei.wei.16|wei.wei.8|wei.wei.2|wei.wei.12|wei.wei.9"Huang, Heyan"https://zbmath.org/authors/?q=ai:huang.heyanSummary: Node classification in structural networks is a longstanding important problem in many real-world applications. Recent studies have shown that network embedding can greatly facilitate node classification by employing embedding algorithms to learn feature representations of nodes. Despite of promising performance, existing network embedding based methods are hard to capture the actual category features of a node because of the linearly inseparable problem in low-dimensional space; meanwhile they cannot incorporate both network structure information and node labels information into the representations simultaneously. To address the above problems, this paper presents a novel Deep Kernel Supervised Hashing (DKSH) method to learn hashing representations of nodes for node classification. Specifically, a deep multiple kernel learning is first employed to map nodes into suitable Hilbert space to deal with linearly inseparable problem. Then, instead of only considering structural similarity between two nodes, a novel similarity matrix is designed to merge both network structure information and node labels information. Supervised by the similarity matrix, the learned hashing representations can preserve the two kinds of information simultaneously from the learned Hilbert space. Extensive experiments show that the proposed method significantly outperforms the state-of-the-art baselines over three real-world benchmark datasets.On the foundations of cycles in Bayesian networkshttps://zbmath.org/1528.683712024-03-13T18:33:02.981707Z"Baier, Christel"https://zbmath.org/authors/?q=ai:baier.christel"Dubslaff, Clemens"https://zbmath.org/authors/?q=ai:dubslaff.clemens"Hermanns, Holger"https://zbmath.org/authors/?q=ai:hermanns.holger"Käfer, Nikolai"https://zbmath.org/authors/?q=ai:kafer.nikolaiSummary: Bayesian networks (BNs) are a probabilistic graphical model widely used for representing expert knowledge and reasoning under uncertainty. Traditionally, they are based on directed acyclic graphs that capture dependencies between random variables. However, directed cycles can naturally arise when cross-dependencies between random variables exist, e.g., for modeling feedback loops. Existing methods to deal with such cross-dependencies usually rely on reductions to BNs without cycles. These approaches are fragile to generalize, since their justifications are intermingled with additional knowledge about the application context. In this paper, we present a foundational study regarding semantics for cyclic BNs that are generic and conservatively extend the cycle-free setting. First, we propose constraint-based semantics that specify requirements for full joint distributions over a BN to be consistent with the local conditional probabilities and independencies. Second, two kinds of limit semantics that formalize infinite unfolding approaches are introduced and shown to be computable by a Markov chain construction.
For the entire collection see [Zbl 1516.68022].NN-EVCLUS: neural network-based evidential clusteringhttps://zbmath.org/1528.683722024-03-13T18:33:02.981707Z"Denœux, Thierry"https://zbmath.org/authors/?q=ai:denoux.thierrySummary: Evidential clustering is an approach to clustering based on the use of Dempster-Shafer mass functions to represent cluster-membership uncertainty. In this paper, we introduce a neural-network based evidential clustering algorithm, called NN-EVCLUS, which learns a mapping from attribute vectors to mass functions, in such a way that more similar inputs are mapped to output mass functions with a lower degree of conflict. The neural network can be paired with a one-class support vector machine to make it robust to outliers and capable of detecting previously unseen clusters when applied to new data. The network is trained to minimize the discrepancy between dissimilarities and degrees of conflict for all or some object pairs. Additional terms can be added to the loss function to account for pairwise constraints or labeled data, which can also be used to adapt the metric. Comparative experiments show the superiority of NN-EVCLUS over state-of-the-art evidential clustering algorithms for a range of unsupervised and constrained clustering tasks involving both attribute and dissimilarity data.Information-theoretic interpretation of quantum formalismhttps://zbmath.org/1528.810082024-03-13T18:33:02.981707Z"Feldmann, Michel"https://zbmath.org/authors/?q=ai:feldmann.michel.1Summary: We present an information-theoretic interpretation of quantum formalism based on a Bayesian framework and devoid of any extra axiom or principle. Quantum information is construed as a technique for analyzing a logical system subject to classical constraints, based on a question-and-answer procedure. The problem is posed from a particular batch of queries while the constraints are represented by the truth table of a set of Boolean functions. The Bayesian inference technique consists in assigning a probability distribution within a real-valued probability space to the joint set of queries in order to satisfy the constraints. The initial query batch is not unique and alternative batches can be considered at will. They are enabled mechanically from the initial batch, quite simply by transcribing the probability space into an auxiliary Hilbert space. It turns out that this sole procedure leads to exactly rediscover the standard quantum information theory and thus provides an information-theoretic rationale to its technical rules. In this framework, the great challenges of quantum mechanics become simple platitudes: Why is the theory probabilistic? Why is the theory linear? Where does the Hilbert space come from? In addition, most of the paradoxes, such as uncertainty principle, entanglement, contextuality, nonsignaling correlation, measurement problem, etc., become straightforward features. In the end, our major conclusion is that quantum information is nothing but classical information processed by a mature form of Bayesian inference technique and, as such, consubstantial with Aristotelian logic.Temporal global correlations in time-symmetric collapse modelshttps://zbmath.org/1528.810152024-03-13T18:33:02.981707Z"Rodríguez-Warnier, Pascal"https://zbmath.org/authors/?q=ai:rodriguez-warnier.pascalSummary: It has been recently argued that by \textit{M. S. Leifer} and \textit{M. F. Pusey} [Proc. R. Soc. Lond., A, Math. Phys. Eng. Sci. 473, No. 2202, Article ID 20160607, 25 p. (2017; Zbl 1402.81020)], and Price, that time-symmetric quantum mechanics must entail retrocausality. Adlam responds that such theories might also entail `spooky action at a distance'. This paper proposes a third alternative: time-symmetric quantum mechanics might entail temporal global correlations. Unlike the traditional analysis of time symmetries in quantum mechanics, which consider linear and unitary interpretations, this paper considers the time-symmetric collapse models advanced by Bedingham and Maroney. These models are specially interesting since it has been widely believed that collapse theories cannot be time-reversal invariant.Can multipartite entanglement be characterized by two-point connected correlation functions?https://zbmath.org/1528.810392024-03-13T18:33:02.981707Z"Lepori, Luca"https://zbmath.org/authors/?q=ai:lepori.luca"Trombettoni, Andrea"https://zbmath.org/authors/?q=ai:trombettoni.andrea"Giuliano, Domenico"https://zbmath.org/authors/?q=ai:giuliano.domenico"Kombe, Johannes"https://zbmath.org/authors/?q=ai:kombe.johannes"Malo, Jorge Yago"https://zbmath.org/authors/?q=ai:malo.jorge-yago"Daley, Andrew J."https://zbmath.org/authors/?q=ai:daley.andrew-j"Smerzi, Augusto"https://zbmath.org/authors/?q=ai:smerzi.augusto"Chiofalo, Maria Luisa"https://zbmath.org/authors/?q=ai:chiofalo.maria-luisaSummary: We discuss under which conditions multipartite entanglement in mixed quantum states can be characterized only in terms of two-point connected correlation functions, as it is the case for pure states. In turn, the latter correlations are defined via a suitable combination of (disconnected) one- and two-point correlation functions. In contrast to the case of pure states, conditions to be satisfied turn out to be rather severe. However, we were able to identify some interesting cases, as when the point-independence is valid of the one-point correlations in each possible decomposition of the density matrix, or when the operators that enter in the correlations are (semi-)positive/negative defined.\(p\)-adic statistical field theory and convolutional deep Boltzmann machineshttps://zbmath.org/1528.811872024-03-13T18:33:02.981707Z"Zúñiga-Galindo, W. A."https://zbmath.org/authors/?q=ai:zuniga-galindo.wilson-a"He, C."https://zbmath.org/authors/?q=ai:he.chengyue|he.conghui.1|he.chen.1|he.chao.2|he.chufan|he.chuhui|he.chenghao|he.canhui|he.chenyuan|he.chunsheng|he.chunxia|he.chenxiang|he.chongnan|he.cong|he.cuiyu|he.changda|he.chenrui|he.changbo|he.chanzi|he.chunyan|he.caiying|he.chunxiong|he.chongchong|he.cuihua|he.chaoan|he.chenwan|he.changjiang|he.chunli|he.chaobo|he.chongyan|he.caixiang|he.chuanping|he.cang|he.chuntian|he.chaobing|he.chenguang|he.chenxu|he.chuan|he.cheng|he.chengdong|he.chunmei|he.chaofan|he.chunxiao|he.chaoming|he.can|he.changxiang|he.congnan|he.chunyang|he.chuanjiang|he.chuning|he.changzheng|he.chengjun|he.chanzhi|he.chunlei|he.chunfang|he.caixia|he.cuizhu|he.chengyuan|he.chunling|he.chaohui|he.chuansheng|he.chunjiang|he.chao|he.chongren|he.cheng.1|he.chuanzhi|he.chuanmei|he.chong|he.canzhi|he.cuijie|he.chunyuan|he.changpeng|he.changzhou|he.chunfa|he.chaoqing|he.caleb|he.chunhua|he.chang|he.chenxi|he.changlian|he.changran|he.chaohua|he.changhong|he.chunwang|he.chu|he.chiyu|he.cunfu|he.chongjun|he.changhua|he.chan|he.chaoyu|he.chaolin|he.changjun|he.chengming|he.changan|he.chunlin|he.chuanfu|he.chenfeng|he.changhan|he.chaodong|he.changli|he.chunjian|he.chun|he.chongyou|he.chenjuan|he.chengqi|he.changbai|he.changming|he.chunjin|he.chiming|he.chuangxin|he.cuiling"Zambrano-Luna, B. A."https://zbmath.org/authors/?q=ai:zambrano-luna.b-aSummary: Understanding how deep learning architectures work is a central scientific problem. Recently, a correspondence between neural networks (NNs) and Euclidean quantum field theories has been proposed. This work investigates this correspondence in the framework of \(p\)-adic statistical field theories (SFTs) and neural networks. In this case, the fields are real-valued functions defined on an infinite regular rooted tree with valence \(p\), a fixed prime number. This infinite tree provides the topology for a continuous deep Boltzmann machine (DBM), which is identified with a statistical field theory on this infinite tree. In the \(p\)-adic framework, there is a natural method to discretize SFTs. Each discrete SFT corresponds to a Boltzmann machine with a tree-like topology. This method allows us to recover the standard DBMs and gives new convolutional DBMs. The new networks use \(O(N)\) parameters while the classical ones use \(O(N^2)\) parameters.Comments on contact terms and conformal manifolds in the AdS/CFT correspondencehttps://zbmath.org/1528.811992024-03-13T18:33:02.981707Z"Sakai, Tadakatsu"https://zbmath.org/authors/?q=ai:sakai.tadakatsu"Zenkai, Masashi"https://zbmath.org/authors/?q=ai:zenkai.masashiSummary: We study the contact terms that appear in the correlation functions of exactly marginal operators using the anti-de Sitter/conformal field theory (AdS/CFT) correspondence. It is known that CFT with an exactly marginal deformation requires the existence of the contact terms with their coefficients having a geometrical interpretation in the context of conformal manifolds. We show that the AdS/CFT correspondence captures properly the mathematical structure of the correlation functions that is expected from the CFT analysis. For this purpose, we employ a holographic renormalization group to formulate a most general setup in the bulk for describing an exactly marginal deformation. The resultant bulk equations of motion are nonlinear and solved perturbatively to obtain the on-shell action. We compute three- and four-point functions of the exactly marginal operators using the GKP-Witten prescription, and show that they match the expected results precisely. The cut-off surface prescription in the bulk serves as a regularization scheme for conformal perturbation theory in the boundary CFT. As an application, we examine a double OPE limit of the four-point functions. The anomalous dimensions of double trace operators are written in terms of the geometrical data of a conformal manifold.Adiabatic quantum algorithm for multijet clustering in high energy physicshttps://zbmath.org/1528.812222024-03-13T18:33:02.981707Z"Pires, Diogo"https://zbmath.org/authors/?q=ai:pires.diogo"Omar, Yasser"https://zbmath.org/authors/?q=ai:omar.yasser"Seixas, João"https://zbmath.org/authors/?q=ai:seixas.joaoSummary: The currently predicted increase in computational demand for the upcoming High-Luminosity Large Hadron Collider (HL-LHC) event reconstruction, and in particular jet clustering, is bound to challenge present day computing resources, becoming an even more complex combinatorial problem. In this paper, we show that quantum annealing can tackle dijet event clustering by introducing a novel quantum annealing binary clustering algorithm. The benchmarked efficiency is of the order of 96\%, thus yielding substantial improvements over the current quantum state-of-the-art. Additionally, we also show how to generalize the proposed objective function into a more versatile form, capable of solving the clustering problem in multijet events.The K-essence flow seen from the preferred frame \(S_V\). A scalar field theory with Landau superfluid structurehttps://zbmath.org/1528.830012024-03-13T18:33:02.981707Z"dos Santos, Rodrigo Francisco"https://zbmath.org/authors/?q=ai:dos-santos.rodrigo-francisco"de Almeida, Luis Gustavo"https://zbmath.org/authors/?q=ai:de-almeida.luis-gustavo"de Faria Junior, Antonio Carlos Amaro"https://zbmath.org/authors/?q=ai:de-faria.antonio-carlos-amaro-junSummary: We study the hypothesis of deformation of the invariance of Lorentz transformations produced by the introduction of a universal minimum velocity relative to a preferred frame. Our goal with this job is to apply this hypothesis to superfluids and study its consequences relating the minimum velocity to the idea of a fluid, with superfluid properties. In previous works we related the minimum velocity to the cosmological constant and even to cosmic inflation. Soon we could generate a hypothetical superfluid capable of modeling with characteristics of a cosmological fluid with dark energy properties. The first excited state of this universal superfluid would be a preferred frame from which all other excited states are observed and then we would have a preferred frame \(S_V\) associated with the critical Landau velocity, thus implying that the universal minimum velocity coincides with the critical Landau velocity, and the objects observed by the preferred frame are excited states of the superfluid. This coincidence between the concepts of minimum velocity and Landau's critical velocity makes Landau's critical velocity a type of limit velocity, modifying the usual causal structure of restricted relativity. Formulating the phenomena in this preferred frame would have the advantage of providing a simple explanation for astrophysical and cosmological phenomena linked to a causal structure, which emerges from this construction and is very similar to causal structures linked to Gordon geometry and acoustic tachyons. We build a deformed relativistic Lagrangian, demonstrate its relation with a \(k\)-essence Lagrangian and calculate the quantities associated with that Lagrangian. We also studied an irrotational fluid and verified the role of enthalpy associated with the minimum velocity structure.Dispersive Friedmann universes and synchronizationhttps://zbmath.org/1528.830062024-03-13T18:33:02.981707Z"Cotsakis, Spiros"https://zbmath.org/authors/?q=ai:cotsakis.spirosSummary: We introduce consideration of dispersive aspects of standard perfect fluid Friedmann cosmology and study the new qualitative behaviours of cosmological solutions that emerge as the fluid parameter changes and zero eigenvalues appear in the linear part of the Friedmann equations. We find that due to their insufficient degeneracy, the Milne, flat, Einstein-static, and de Sitter solutions cannot properly bifurcate. However, the dispersive versions of Milne and flat universes contained in the versal unfolding of the standard Friedmann equations possess novel long-term properties not met in their standard counterparts. We apply these results to the horizon problem and show that unlike their hyperbolic versions, the dispersive Milne and flat solutions completely synchronize in the future, hence offering a solution to the homogeneity, isotropy, and causal connectedness puzzles.Revisiting the renormalization of Einstein-Maxwell theory at one-loophttps://zbmath.org/1528.830082024-03-13T18:33:02.981707Z"Park, I. Y."https://zbmath.org/authors/?q=ai:park.il-young|park.inyong-ySummary: In a series of recent works based on foliation-based quantization in which renormalizability has been achieved for the physical sector of the theory, we have shown that the use of the standard graviton propagator interferes, due to the presence of the trace mode, with the four-dimensional covariance. A subtlety in the background field method also requires careful handling. This status of the matter motivated us to revisit an Einstein-scalar system in one of the sequels. Continuing the endeavors, we revisit the one-loop renormalization of an Einstein-Maxwell system in the present work. The systematic renormalization of the cosmological and Newton constants is carried out by applying the refined background field method. The one-loop beta function of the vector coupling constant is explicitly computed and compared with the literature. The longstanding problem of the gauge choice dependence of the effective action is addressed, and the manner in which gauge choice independence is restored in the present framework is discussed. The formalism also sheds light on background independent analysis. The renormalization involves a metric field redefinition originally introduced by 't Hooft; with the field redefinition the theory should be predictive.Thermal expansion of atmosphere and stability of vertically stratified fluidshttps://zbmath.org/1528.830122024-03-13T18:33:02.981707Z"Kaladze, T. D."https://zbmath.org/authors/?q=ai:kaladze.t-d"Misra, A. P."https://zbmath.org/authors/?q=ai:misra.amar-p|misra.arun-prabhaSummary: The influence of thermal expansion of the Earth's atmosphere on the stability of vertical stratification of fluid density and temperature is studied. We show that such an influence leads to the instability of incompressible flows. Modified by the thermal expansion coefficient, a new expression for the Brunt-Väisälä frequency is derived, and a critical value of the thermal expansion coefficient for which the instability occurs is revealed.Null geodesics from ladder moleculeshttps://zbmath.org/1528.830362024-03-13T18:33:02.981707Z"Bhattacharya, Anish"https://zbmath.org/authors/?q=ai:bhattacharya.anish"Mathur, Abhishek"https://zbmath.org/authors/?q=ai:mathur.abhishek"Surya, Sumati"https://zbmath.org/authors/?q=ai:surya.sumatiSummary: We propose a discrete analogue of null geodesics in causal sets that are approximated by \(\mathbb{M}^2\), in the spirit of Kronheimer and Penrose's ``grids'' and ``beams'' for an abstract causal space. The causal set analogues are ``ladder molecules'', whose rungs are linked pairs of elements corresponding loosely to \textit{C. Barton} et al's horizon bi-atoms [Phys. Rev. D (3) 100, No. 12, Article ID 126008, 17 p. (2019; \url{doi:10.1103/PhysRevD.100.126008})]. In \(\mathbb{M}^2\) a ladder molecule traps a ribbon of null geodesics corresponding to a thickened or fuzzed out horizon. The existence of a ladder between linked pairs of elements in turn provides a generalisation of the horismotic relation to causal sets. Simulations of causal sets approximated by a region of \(\mathbb{M}^2\) show that ladder molecules are fairly dense in the causal set, and provide a light-cone like grid. Moreover, similar to the uniqueness of null geodesics between horismotically related events in \(\mathbb{M}^2\), in such causal sets there is a unique ladder molecule between any two linked pairs which are related by the generalised horismotic relation.Data-driven and almost model-independent reconstruction of modified gravityhttps://zbmath.org/1528.830542024-03-13T18:33:02.981707Z"Mu, Yuhao"https://zbmath.org/authors/?q=ai:mu.yuhao"Li, En-Kun"https://zbmath.org/authors/?q=ai:li.en-kun"Xu, Lixin"https://zbmath.org/authors/?q=ai:xu.lixin.1(no abstract)Birth of baby universes from gravitational collapse in a modified-gravity scenariohttps://zbmath.org/1528.831042024-03-13T18:33:02.981707Z"Masó-Ferrando, Andreu"https://zbmath.org/authors/?q=ai:maso-ferrando.andreu"Sanchis-Gual, Nicolas"https://zbmath.org/authors/?q=ai:sanchis-gual.nicolas"Font, José A."https://zbmath.org/authors/?q=ai:font.jose-antonio"Olmo, Gonzalo J."https://zbmath.org/authors/?q=ai:olmo.gonzalo-j(no abstract)Coupling quintessence kinetics to electromagnetismhttps://zbmath.org/1528.831252024-03-13T18:33:02.981707Z"Barros, Bruno J."https://zbmath.org/authors/?q=ai:barros.bruno-jose-s"da Fonseca, Vitor"https://zbmath.org/authors/?q=ai:da-fonseca.vitor(no abstract)Stability of domain wall network with initial inflationary fluctuations and its implications for cosmic birefringencehttps://zbmath.org/1528.831422024-03-13T18:33:02.981707Z"Gonzalez, Diego"https://zbmath.org/authors/?q=ai:gonzalez.diego-luiz|gonzalez.diego-luis"Kitajima, Naoya"https://zbmath.org/authors/?q=ai:kitajima.naoya"Takahashi, Fuminobu"https://zbmath.org/authors/?q=ai:takahashi.fuminobu"Yin, Wen"https://zbmath.org/authors/?q=ai:yin.wenSummary: We study the formation and evolution of domain walls with initial inflationary fluctuations by numerical lattice calculations that, for the first time, correctly take into account correlations on superhorizon scales. We find that, contrary to the widely-held claim over the past few tens of years, the domain wall network exhibits remarkable stability even when the initial distribution is largely biased toward one of the minima. This is due to the fact that the domain wall network retains information about initial conditions on superhorizon scales, and that the scaling solution is not a local attractor in this sense. Our finding immediately implies that such domain walls will have a significant impact on cosmology, including the production of gravitational waves, baryogenesis, and dark matter from domain walls. Applying this result to the axion-like particle domain wall, we show that it not only explains the isotropic cosmic birefringence suggested by the recent analysis, but also predicts anisotropic cosmic birefringence that is nearly scale-invariant on large scales and can be probed by future CMB observations.A viable varying speed of light model in the RW metrichttps://zbmath.org/1528.831462024-03-13T18:33:02.981707Z"Lee, Seokcheon"https://zbmath.org/authors/?q=ai:lee.seokcheonSummary: The Robertson-Walker (RW) metric allows us to apply general relativity to model the behavior of the Universe as a whole (i.e., cosmology). We can properly interpret various cosmological observations, like the cosmological redshift, the Hubble parameter, geometrical distances, and so on, if we identify fundamental observers with individual galaxies. That is to say that the interpretation of observations of modern cosmology relies on the RW metric. The RW model satisfies the cosmological principle in which the 3-space always remains isotropic and homogeneous. One can derive the cosmological redshift relation from this condition. We show that it is still possible for us to obtain consistent results in a specific time-varying speed-of-light model without spoiling the success of the standard model. The validity of this model needs to be determined by observations.Exact parallel waves in general relativityhttps://zbmath.org/1528.831562024-03-13T18:33:02.981707Z"Roche, Cian"https://zbmath.org/authors/?q=ai:roche.cian"Aazami, Amir Babak"https://zbmath.org/authors/?q=ai:aazami.amir-babak"Cederbaum, Carla"https://zbmath.org/authors/?q=ai:cederbaum.carlaSummary: We conduct a review of the basic definitions and the principal results in the study of wavelike spacetimes, that is spacetimes whose metric models massless radiation moving at the speed of light, focusing in particular on those geometries \textit{with parallel rays}. In particular, we motivate and connect their various definitions, outline their coordinate descriptions and present some classical results in their study in a language more accessible to modern readers, including the existence of ``null coordinates'' and the construction of Penrose limits. We also present a thorough summary of recent work on causality in pp-waves, and describe progress in addressing an open question in the field -- the Ehlers-Kundt conjecture.Bootstrapping multi-field inflation: non-Gaussianities from light scalars revisitedhttps://zbmath.org/1528.831712024-03-13T18:33:02.981707Z"Wang, Dong-Gang"https://zbmath.org/authors/?q=ai:wang.dong-gang"Pimentel, Guilherme L."https://zbmath.org/authors/?q=ai:pimentel.guilherme-l"Achúcarro, Ana"https://zbmath.org/authors/?q=ai:achucarro.anaSummary: Primordial non-Gaussianities from multi-field inflation are a leading target for cosmological observations, because of the possible large correlations generated between long and short distances. These signatures are captured by the local shape of the scalar bispectrum. In this paper, we revisit the nonlinearities of the conversion process from additional light scalars into curvature perturbations during inflation. We provide analytic templates for correlation functions valid at any kinematical configuration, using the cosmological bootstrap as a main computational tool. Our results include the possibility of large breaking of boost symmetry, in the form of small speeds of sound for both the inflaton and the mediators. We consider correlators coming from the tree-level exchange of a massless scalar field. By introducing a late-time cutoff, we identify that the symmetry constraints on the correlators are modified. This leads to anomalous conformal Ward identities, and consequently the bootstrap differential equations acquire a source term that depends on this cutoff. The solutions to the differential equations are scalar seed functions that incorporate these late-time growth effects. Applying weight-shifting operators to auxiliary ``seed'' functions, we obtain a systematic classification of shapes of non-Gaussianity coming from massless exchange. For theories with de Sitter symmetry, we compare the resulting shapes with the ones obtained via the \(\delta N\) formalism, identifying missing contributions away from the squeezed limit. For boost-breaking scenarios, we derive a novel class of shape functions with phenomenologically distinct features in scale-invariant theories. Specifically, the new shape provides a simple extension of equilateral non-Gaussianity: the signal peaks at a geometric configuration controlled by the ratio of the sound speeds of the mediator and the inflaton.Stochastic reconstruction of shale combining multi-scale generators and discriminators with attention mechanismshttps://zbmath.org/1528.860112024-03-13T18:33:02.981707Z"Zhang, Ting"https://zbmath.org/authors/?q=ai:zhang.ting.4"Dong, Yue"https://zbmath.org/authors/?q=ai:dong.yue"Bai, Hualin"https://zbmath.org/authors/?q=ai:bai.hualin"Peng, Yuan"https://zbmath.org/authors/?q=ai:peng.yuanSummary: The development of shale gas can optimize the energy structure and alleviate the sharp contradiction between energy supplies and demands. Stochastic simulation of shale reservoirs is a common and practical method for predicting and evaluating shale gas distribution and extent. Shale has complex pore structure, strong heterogeneity and low permeability with multi-scale natural fractures, which makes it difficult to characterize or simulate using common numerical simulation methods. Generative adversarial network (GAN), as the mainstream generative model of recently flourishing deep learning methods, can theoretically learn any feature distribution of training images and generate fake images that are similar to real ones, which has been successfully used in geological stochastic simulation. The original GAN is unstable due to the defect of the loss function and its structure, possibly leading to significant differences between the reconstructed results and the real samples. Moreover, the ability of extracting features from the original GAN is restricted by the demand of a large number of training datasets, which makes a difficult prerequisite for shale reconstruction. The multi-scale structure can capture the characteristics of shale at different scales, suitable for multi-scale internal structure of shale. Attention mechanisms can focus on important information and suppress unwanted information. Therefore, a multi-scale GAN combining with attention mechanisms for 3D shale reconstruction is proposed based on only one shale image. The original GAN's loss function is replaced by the hinge-GAN loss function. By comparing with other methods using various measurement metrics, it is proved that our method is effective in shale reconstruction and has good consistency in physical properties with the real data.Observability transitions in clustered networkshttps://zbmath.org/1528.900552024-03-13T18:33:02.981707Z"Hasegawa, Takehisa"https://zbmath.org/authors/?q=ai:hasegawa.takehisa"Iwase, Yuta"https://zbmath.org/authors/?q=ai:iwase.yutaSummary: We investigate the effect of clustering on network observability transitions. In the observability model introduced by \textit{Y. Yang} et al. [Phys. Rev. Lett. 109, No. 25, Article ID 019902 , 5 p. (2012; \url{doi:10.1103/PhysRevLett.109.258701})], a given fraction of nodes are chosen randomly, and they and those neighbors are considered to be observable, while the other nodes are unobservable. For the observability model on random clustered networks, we derive the normalized sizes of the largest observable component (LOC) and largest unobservable component (LUC). Considering the case where the numbers of edges and triangles of each node are given by the Poisson distribution, we find that both LOC and LUC are affected by the network's clustering: more highly-clustered networks have lower critical node fractions for forming macroscopic LOC and LUC, but this effect is small, becoming almost negligible unless the average degree is small. We also evaluate bounds for these critical points to confirm clustering's weak or negligible effect on the network observability transition. The accuracy of our analytical treatment is confirmed by Monte Carlo simulations.On mixed censored \(\delta \)-shock modelshttps://zbmath.org/1528.900892024-03-13T18:33:02.981707Z"Chadjiconstantinidis, Stathis"https://zbmath.org/authors/?q=ai:chadjiconstantinidis.stathisSummary: In this paper we introduce the mixed censored \(\delta \)-shock model which combines the censored \(\delta \)-shock model and the classical extreme shock model. Under the mixed censored \(\delta \)-shock model, the system fails whenever no shock occurs within a \(\delta \)-length time period from the last shock, or the magnitude of the shock is larger than another critical threshold \(\gamma > 0\). For the discrete-time case of occurrence of shocks, by assuming the dependence between intershock times and the corresponding magnitudes of shocks we derive the probability generating function (pgf) of the lifetime of the system, and a matrix-based expression is obtained for the exact distribution of the system's lifetime when the distribution of intershock times and the magnitudes of shocks have a discrete bivariate phase-type distribution. Similar results are obtained by assuming the independence between intershock times and the corresponding magnitudes of shocks, and by proving that the distribution of the shifted lifetime at \(\delta \), is the convolution of a discrete compound geometric distribution and a discrete compound Bernoulli distribution, we get several results concerning the distribution of system's lifetime, like as, simple and efficient recursions for evaluating the survival function and the probability mass function (pmf), the mean and the variance of system's lifetime, as well as discrete Lundberg-type upper bounds for the reliability function. For the continuous-time case of occurrence of shocks we obtain an exact formula for the reliability function and the Laplace-Stieltjes transform of system's lifetime by assuming the dependence between intershock times and the corresponding magnitudes of shocks, and under the independence setup, we obtain the reliability function when the intershock times have the uniform distribution, and we give an asymptotic result under the Poisson process for the arrival of shocks. Similar to the discrete-time case, it is shown that the distribution of the shifted lifetime at \(\delta \), is the convolution of a compound geometric distribution and a compound Bernoulli distribution and using this we obtain two-sided Lundberg-type bounds for the survival function. Finally, some numerical examples to illustrate our results, are also given.Optimal task-driven time-dependent covariate-based maintenance policyhttps://zbmath.org/1528.900942024-03-13T18:33:02.981707Z"Misaii, Hasan"https://zbmath.org/authors/?q=ai:misaii.hasan"Fouladirad, Mitra"https://zbmath.org/authors/?q=ai:fouladirad.mitra"Haghighi, Firoozeh"https://zbmath.org/authors/?q=ai:haghighi.firoozehSummary: In this paper, a multi-component series system is considered. The system is monitored periodically. The exact cause of failure is assumed to be masked or missed. In the masked setup, the exact cause of failure is unknown but the set to which it belongs, called the masked set, is known. While in the missing setup, there is no information about the exact cause of failure. A time-dependent covariate-based maintenance policy is proposed such that the maintenance action and cost of the failed components at inspection times depend on several factors and can vary. The component lifetime distributions are considered unknown. The proposed maintenance policy is optimized using some task-driven decision-making statistical learning methods. Finally, the applicability of the proposed theory is analyzed through some numerical analysis. The results are compared to the case where lifetime distributions are known as a benchmark.Semi-supervised \(k\)-means clustering via DC programming approachhttps://zbmath.org/1528.901962024-03-13T18:33:02.981707Z"Gruzdeva, Tatiana V."https://zbmath.org/authors/?q=ai:gruzdeva.tatiana-v"Ushakov, Anton V."https://zbmath.org/authors/?q=ai:ushakov.anton-vladimirovichSummary: Though clustering is related to unsupervised machine learning and does not require any prior information on data items, in many real-life settings, there may be some expert knowledge on data labels or the properties of clusters known in advance. Obviously, such knowledge may be used to guide clustering process and improve the quality of found partitions. The clustering problems that involve some additional information on tags are called semi-supervised or constrained clustering problems. One distinguishes instance-level and cluster-level constraints usually formalized as the so-called must-link and cannot-link constraints or minimum/maximum cluster size. In this paper, we consider the constrained minimum sum-of-squares (\(k\)-means) clustering (MSSC) problem that incorporates both instance- and cluster-level constraints. As far as we know, such a semi-supervised MSSC problem has not been considered in the literature yet. We formulate this clustering problem and some of its particular cases as DC (difference of convex) optimization problems. Then, we develop a solution approach based on a special local search method. We carry out computational experiments on test problem instances demonstrating the efficiency of the proposed solution approach.
For the entire collection see [Zbl 1517.90002].Pricing Bermudan options using regression trees/random forestshttps://zbmath.org/1528.910732024-03-13T18:33:02.981707Z"Ech-Chafiq, Zineb El Filali"https://zbmath.org/authors/?q=ai:el-filali-ech-chafiq.zineb"Labordère, Pierre Henry"https://zbmath.org/authors/?q=ai:henry-labordere.pierre"Lelong, Jérôme"https://zbmath.org/authors/?q=ai:lelong.jeromeSummary: The value of an American option is the maximized value of the discounted cash flows from the option. At each time step, one needs to compare the immediate exercise value with the continuation value and decide to exercise as soon as the exercise value is strictly greater than the continuation value. We can formulate this problem as a dynamic programming equation, where the main difficulty comes from the computation of the conditional expectations representing the continuation values at each time step. In [\textit{F. A. Longstaff} and \textit{E. S. Schwartz}, Rev. Financ. Stud. 6, No. 2, 327--343 (1993; Zbl 1386.91144)], these conditional expectations were estimated using regressions on a finite-dimensional vector space (typically a polynomial basis). In this paper, we follow the same algorithm; only the conditional expectations are estimated using regression trees or random forests. We discuss the convergence of the Longstaff and Schwartz algorithm when the standard least squares regression is replaced by regression trees. Finally, we expose some numerical results with regression trees and random forests. The random forest algorithm gives excellent results in high dimensions.Bayesian inference on the Allee effect in cancer cell line populations using time-lapse microscopy imageshttps://zbmath.org/1528.920152024-03-13T18:33:02.981707Z"Lindwall, Gustav"https://zbmath.org/authors/?q=ai:lindwall.gustav"Gerlee, Philip"https://zbmath.org/authors/?q=ai:gerlee.philipSummary: The Allee effect describes the phenomenon that the per capita reproduction rate increases along with the population density at low densities. Allee effects have been observed at all scales, including in microscopic environments where individual cells are taken into account. This is great interest to cancer research, as understanding critical tumour density thresholds can inform treatment plans for patients. In this paper, we introduce a simple model for cell division in the case where the cancer cell population is modelled as an interacting particle system. The rate of the cell division is dependent on the local cell density, introducing an Allee effect. We perform parameter inference of the key model parameters through Markov chain Monte Carlo, and apply our procedure to two image sequences from a cervical cancer cell line. The inference method is verified on \textit{in silico} data to accurately identify the key parameters, and results on the \textit{in vitro} data strongly suggest an Allee effect.Geometric science of information. 6th international conference, GSI 2023, St. Malo, France, August 30 -- September 1, 2023. Proceedings. Part Ihttps://zbmath.org/1528.940032024-03-13T18:33:02.981707ZThe articles of this volume will be reviewed individually. For the preceding conference see [Zbl 1482.94007]. For Part II of the proceedings of the present conference see [Zbl 1528.53002].
Indexed articles:
\textit{Tumpach, Alice Barbora; Preston, Stephen C.}, Three methods to put a Riemannian metric on shape space, 3-11 [Zbl 07789178]
\textit{Maignant, Elodie; Trouvé, Alain; Pennec, Xavier}, Riemannian locally linear embedding with application to Kendall shape spaces, 12-20 [Zbl 07789179]
\textit{Pryymak, Lidiya; Suchan, Tim; Welker, Kathrin}, A product shape manifold approach for optimizing piecewise-smooth shapes, 21-30 [Zbl 07789180]
\textit{Tumpach, Alice Barbora}, On canonical parameterizations of 2D-shapes, 31-40 [Zbl 07789181]
\textit{Ciuclea, Ioana; Tumpach, Alice Barbora; Vizman, Cornelia}, Shape spaces of nonlinear flags, 41-50 [Zbl 07789182]
\textit{Bolelli, Maria Virginia; Citti, Giovanna; Sarti, Alessandro; Zucker, Steven}, A neurogeometric stereo model for individuation of 3D perceptual units, 53-62 [Zbl 07789183]
\textit{Pai, Gautam; Bellaard, Gijs; Smets, Bart M. N.; Duits, Remco}, Functional properties of PDE-based group equivariant convolutional neural networks, 63-72 [Zbl 07789184]
\textit{Vadgama, Sharvaree; Tomczak, Jakub M.; Bekkers, Erik}, Continuous Kendall shape variational autoencoders, 73-81 [Zbl 07789185]
\textit{Velasco-Forero, Santiago}, Can generalised divergences help for invariant neural networks?, 82-90 [Zbl 07789186]
\textit{Shewmake, Christian; Miolane, Nina; Olshausen, Bruno}, Group equivariant sparse coding, 91-101 [Zbl 07789187]
\textit{Broniatowski, Michel; Stummer, Wolfgang}, On a cornerstone of bare-simulation distance/divergence optimization, 105-116 [Zbl 07789188]
\textit{Girardin, Valérie; Regnault, Philippe}, Extensive entropy functionals and non-ergodic random walks, 117-124 [Zbl 07789189]
\textit{Boukeloua, Mohamed; Keziou, Amor}, Empirical likelihood with censored data, 125-135 [Zbl 07789190]
\textit{Baudry, Jean-Patrick; Broniatowski, Michel; Thommeret, Cyril}, Aggregated tests based on supremal divergence estimators for non-regular statistical models, 136-144 [Zbl 07789191]
\textit{Nielsen, Frank}, Quasi-arithmetic centers, quasi-arithmetic mixtures, and the Jensen-Shannon \(\nabla \)-divergences, 147-156 [Zbl 07789192]
\textit{Tanaka, Hisatoshi}, Geometry of parametric binary choice models, 157-166 [Zbl 07789193]
\textit{Tojo, Koichi; Yoshino, Taro}, A \(q\)-analogue of the family of Poincaré distributions on the upper half plane, 167-175 [Zbl 07789194]
\textit{Nielsen, Frank; Okamura, Kazuki}, On the \(f\)-divergences between hyperboloid and Poincaré distributions, 176-185 [Zbl 07789195]
\textit{Cheng, Kaiming; Zhang, Jun}, \( \lambda \)-deformed evidence lower bound (\( \lambda \)-ELBO) using Rényi and Tsallis divergence, 186-196 [Zbl 07789196]
\textit{Opozda, Barbara}, On the tangent bundles of statistical manifolds, 199-206 [Zbl 07789197]
\textit{Mama Assandje, Prosper Rosaire; Dongho, Joseph}, Geometric properties of beta distributions, 207-216 [Zbl 07789198]
\textit{Herguey, Mopeng; Dongho, Joseph}, KV cohomology group of some KV structures on \(\mathbb{R}^2\), 217-225 [Zbl 07789199]
\textit{Yoshioka, Masaki; Tanaka, Fuyuhiko}, Alpha-parallel priors on a one-sided truncated exponential family, 226-235 [Zbl 07789200]
\textit{Subrahamanian Moosath, K. S.; Mahesh, T. V.}, Conformal submersion with horizontal distribution and geodesics, 236-243 [Zbl 07789201]
\textit{Mainiero, Tom}, Higher information from families of measures, 247-257 [Zbl 07789202]
\textit{Sergeant-Perthuis, Grégoire}, A categorical approach to statistical mechanics, 258-267 [Zbl 07789203]
\textit{Perrone, Paolo}, Categorical information geometry, 268-277 [Zbl 07789204]
\textit{Chen, Stephanie; Vigneaux, Juan Pablo}, Categorical magnitude and entropy, 278-287 [Zbl 07789205]
\textit{Rioul, Olivier}, A historical perspective on Schützenberger-Pinsker inequalities, 291-306 [Zbl 07789206]
\textit{Florin, Franck}, On Fisher information matrix, array manifold geometry and time delay estimation, 307-317 [Zbl 07789207]
\textit{Meneghetti, Fábio C. C.; Miyamoto, Henrique K.; Costa, Sueli I. R.; Costa, Max H. M.}, Revisiting lattice tiling decomposition and dithered quantisation, 318-327 [Zbl 07789208]
\textit{Wolfer, Geoffrey; Watanabe, Shun}, Geometric reduction for identity testing of reversible Markov chains, 328-337 [Zbl 07789209]
\textit{Vigneaux, Juan Pablo}, On the entropy of rectifiable and stratified measures, 338-346 [Zbl 07789210]
\textit{Ulmer, Susanne; Van, Do Tran; Huckemann, Stephan F.}, Exploring uniform finite sample stickiness, 349-356 [Zbl 07789211]
\textit{Lammers, Lars; Van, Do Tran; Nye, Tom M. W.; Huckemann, Stephan F.}, Types of stickiness in BHV phylogenetic tree spaces and their degree, 357-365 [Zbl 07789212]
\textit{Calissano, Anna; Maignant, Elodie; Pennec, Xavier}, Towards quotient barycentric subspaces, 366-374 [Zbl 07789213]
\textit{Szwagier, Tom; Pennec, Xavier}, Rethinking the Riemannian logarithm on flag manifolds as an orthogonal alignment problem, 375-383 [Zbl 07789214]
\textit{Thanwerdas, Yann; Pennec, Xavier}, Characterization of invariant inner products, 384-391 [Zbl 07789215]
\textit{Lambert, Marc; Bonnabel, Silvère; Bach, Francis}, Variational Gaussian approximation of the Kushner optimal filter, 395-404 [Zbl 07789216]
\textit{Han, Andi; Mishra, Bamdev; Jawanpuria, Pratik; Gao, Junbin}, Learning with symmetric positive definite matrices via generalized Bures-Wasserstein geometry, 405-415 [Zbl 07789217]
\textit{Minh, Hà Quang}, Fisher-Rao Riemannian geometry of equivalent Gaussian measures on Hilbert space, 416-425 [Zbl 07789218]
\textit{Da Costa, Nathaël; Mostajeran, Cyrus; Ortega, Juan-Pablo}, The Gaussian kernel on the circle and spaces that admit isometric embeddings of the circle, 426-435 [Zbl 07789219]
\textit{Said, Salem; Mostajeran, Cyrus}, Determinantal expressions of certain integrals on symmetric spaces, 436-443 [Zbl 07789220]
\textit{Chevallier, Emmanuel}, Projective Wishart distributions, 444-451 [Zbl 07789221]
\textit{Améndola, Carlos; Lee, Darrick; Meroni, Chiara}, Convex hulls of curves: volumes and signatures, 455-464 [Zbl 07789222]
\textit{Caravantes, Jorge; Diaz-Toca, Gema M.; Gonzalez-Vega, Laureano}, Avoiding the general position condition when computing the topology of a real algebraic plane curve defined implicitly, 465-473 [Zbl 07789223]
\textit{Gakkhar, Sita; Marcolli, Matilde}, Dynamical geometry and a persistence \(K\)-theory in noisy point clouds, 474-483 [Zbl 07789224]
\textit{Vermeylen, Charlotte; Olikier, Guillaume; Van Barel, Marc}, An approximate projection onto the tangent cone to the variety of third-order tensors of bounded tensor-train rank, 484-493 [Zbl 07789225]
\textit{Duarte, Eliana; Hollering, Benjamin; Wiesmann, Maximilian}, Toric fiber products in geometric modeling, 494-503 [Zbl 07789226]
\textit{Aniello, Paolo}, Twirled products and group-covariant symbols, 507-515 [Zbl 07789227]
\textit{Barron, Tatyana; Kazachek, Alexander}, Coherent states and entropy, 516-523 [Zbl 07789228]
\textit{Bieliavsky, Pierre; Dendoncker, Valentin}, A non-formal formula for the Rankin-Cohen deformation quantization, 524-532 [Zbl 07789229]
\textit{Bieliavsky, Pierre; Dendoncker, Valentin; Korvers, Stéphane}, Equivalence of invariant star-products: the ``retract'' method, 533-539 [Zbl 07789230]
\textit{Erzmann, David; Dittmer, Sören; Harms, Henrik; Maaß, Peter}, \texttt{DL4TO}: a deep learning library for sample-efficient topology optimization, 543-551 [Zbl 07789231]
\textit{Noren, Håkon}, Learning Hamiltonian systems with mono-implicit Runge-Kutta methods, 552-559 [Zbl 07789232]
\textit{Sutton, Oliver J.; Gorban, Alexander N.; Tyukin, Ivan Y.}, A geometric view on the role of nonlinear feature maps in few-shot learning, 560-568 [Zbl 07789233]
\textit{Offen, Christian; Ober-Blöbaum, Sina}, Learning discrete Lagrangians for variational PDEs from data and detection of travelling waves, 569-579 [Zbl 07789234]
\textit{Huang, Qiao; Zambrini, Jean-Claude}, Gauge transformations in stochastic geometric mechanics, 583-591 [Zbl 07789235]
\textit{Bénéfice, Magalie; Arnaudon, Marc; Bonnefont, Michel}, Couplings of Brownian motions on \(\mathrm{SU}(2,\mathbb{C})\), 592-600 [Zbl 07789236]
\textit{Bhauryal, Neeraj}, A finite volume scheme for fractional conservation laws driven by Lévy noise, 601-609 [Zbl 07789237]
\textit{Chambolle, Antonin; Duval, Vincent; Machado, João Miguel}, The total variation-Wasserstein problem: a new derivation of the Euler-Lagrange equations, 610-619 [Zbl 07789238]Multiterminal statistical inference: an unsolved problemhttps://zbmath.org/1528.940122024-03-13T18:33:02.981707Z"Amari, Shun-Ichi"https://zbmath.org/authors/?q=ai:amari.shun-ichiSummary: We describe an unsolved statistical inference problem involving two correlated signals \(x\) and \(y\). When correlated random variables \(x\) and \(y\) are observed repeatedly at separate locations, we need to send them to a common location where statistical inference takes place. We consider the situation when the transmission rates of the \(x\)'s and \(y\)'s are limited. What is the best encoding plan for the \(x\)'s and \(y\)'s under this restriction? This problem, integrating information theory and statistics, looks very easy. However, more than 40 years have passed without significant progress. We elucidate this problem by using simple examples.
For the entire collection see [Zbl 1515.01005].Distributionally robust optimization by probability criterion for estimating a bounded signalhttps://zbmath.org/1528.940182024-03-13T18:33:02.981707Z"Semenikhin, Konstantin"https://zbmath.org/authors/?q=ai:semenikhin.konstantin-v"Arkhipov, Alexandr"https://zbmath.org/authors/?q=ai:arkhipov.alexandrSummary: This paper aims at solving a distributionally robust minimax estimation problem to recover a bounded smooth signal from the finite number of measurements with known second-order moment characteristics of the observation noise. The objective functional is the probability that the L2-norm of the estimation error will exceed a given threshold. To take into account the prior uncertainty, the upper bound of the probability functional is considered over the family of noise distributions and the set of signals with bounded second derivative. The goal of the problem is to minimize the worst-case error probability over the class of linear estimators. A specific feature of this problem is a major significance of the bias and its guaranteed bound. To solve the robust optimization problem with the probability objective we follow two methods: 1) direct minimization of the MSE-bound derived from the Markov inequality; 2) applying the explicit multivariate Selberg bound to the problem with quantile criterion. Numerical simulations are performed to compare the two methods applied to the problem of target path recovery.
For the entire collection see [Zbl 1517.90002].Generic attack on duplex-based AEAD modes using random function statisticshttps://zbmath.org/1528.940532024-03-13T18:33:02.981707Z"Gilbert, Henri"https://zbmath.org/authors/?q=ai:gilbert.henri"Heim Boissier, Rachelle"https://zbmath.org/authors/?q=ai:boissier.rachelle-heim"Khati, Louiza"https://zbmath.org/authors/?q=ai:khati.louiza"Rotella, Yann"https://zbmath.org/authors/?q=ai:rotella.yannSummary: Duplex-based authenticated encryption modes with a sufficiently large key length are proven to be secure up to the birthday bound \(2^{\frac{c}{2}} \), where \(c\) is the capacity. However this bound is not known to be tight and the complexity of the best known generic attack, which is based on multicollisions, is much larger: it reaches \(\frac{2^c}{\alpha }\) where \(\alpha\) represents a small security loss factor. There is thus an uncertainty on the true extent of security beyond the bound \(2^{\frac{c}{2}}\) provided by such constructions. In this paper, we describe a new generic attack against several duplex-based AEAD modes. Our attack leverages random functions statistics and produces a forgery in time complexity \(\mathcal{O}(2^{\frac{3c}{4}})\) using negligible memory and no encryption queries. Furthermore, for some duplex-based modes, our attack recovers the secret key with a negligible amount of additional computations. Most notably, our attack breaks a security claim made by the designers of the NIST lightweight competition candidate \textsc{Xoodyak}. This attack is a step further towards determining the exact security provided by duplex-based constructions.
For the entire collection see [Zbl 1525.94004].