×

zbMATH — the first resource for mathematics

Deep learning and k-means clustering in heterotic string vacua with line bundles. (English) Zbl 1437.83145
Summary: We apply deep-learning techniques to the string landscape, in particular, SO(32) heterotic string theory on simply-connected Calabi-Yau threefolds with line bundles. It turns out that three-generation models cluster in particular islands specified by deep autoencoder networks and k-means++ clustering. Especially, we explore mutual relations between model parameters and the cluster with densest three-generation models (called “3-generation island”). We find that the 3-generation island has a strong correlation with the topological data of Calabi-Yau threefolds, in particular, second Chern class of the tangent bundle of the Calabi-Yau threefolds. Our results also predict a large number of Higgs pairs in the 3-generation island.
MSC:
83E30 String and superstring theories in gravitational theory
14J32 Calabi-Yau manifolds (algebro-geometric aspects)
32Q25 Calabi-Yau theory (complex-analytic aspects)
PDF BibTeX XML Cite
Full Text: DOI arXiv
References:
[1] Y.-H. He, Deep-learning the landscape, arXiv:1706.02714 [INSPIRE].
[2] He, Y-H, Machine-learning the string landscape, Phys. Lett., B 774, 564 (2017)
[3] Krefl, D.; Seong, R-K, Machine learning of Calabi-Yau volumes, Phys. Rev., D 96 (2017)
[4] Ruehle, F., Evolving neural networks with genetic algorithms to study the String Landscape, JHEP, 08, 038 (2017) · Zbl 1381.83128
[5] Carifio, J.; Halverson, J.; Krioukov, D.; Nelson, BD, Machine learning in the string landscape, JHEP, 09, 157 (2017) · Zbl 1382.81155
[6] Mütter, A.; Parr, E.; Vaudrevange, PKS, Deep learning in the heterotic orbifold landscape, Nucl. Phys., B 940, 113 (2019) · Zbl 1409.81099
[7] Bull, K.; He, Y-H; Jejjala, V.; Mishra, C., Getting CICY High, Phys. Lett., B 795, 700 (2019) · Zbl 1420.14002
[8] Halverson, J.; Nelson, B.; Ruehle, F., Branes with brains: exploring string vacua with deep reinforcement learning, JHEP, 06, 003 (2019) · Zbl 1416.83125
[9] Cole, A.; Schachner, A.; Shiu, G., Searching the landscape of flux vacua with genetic algorithms, JHEP, 11, 045 (2019) · Zbl 1429.83085
[10] M. Larfors and R. Schneider, Explore and exploit with heterotic line bundle models, arXiv:2003.04817.
[11] A. Ashmore, Y.-H. He and B.A. Ovrut, Machine learning Calabi-Yau metrics, arXiv:1910.08605 [INSPIRE].
[12] Ruehle, F., Data science applications to string theory, Phys. Rept., 839, 1 (2020) · Zbl 1452.81004
[13] Beasley, C.; Heckman, JJ; Vafa, C., GUTs and exceptional branes in F-theory — II: experimental predictions, JHEP, 01, 059 (2009) · Zbl 1243.81141
[14] Donagi, R.; Wijnholt, M., Breaking GUT groups in F-theory, Adv. Theor. Math. Phys., 15, 1523 (2011) · Zbl 1269.81121
[15] Blumenhagen, R.; Honecker, G.; Weigand, T., Loop-corrected compactifications of the heterotic string with line bundles, JHEP, 06, 020 (2005)
[16] Blumenhagen, R.; Honecker, G.; Weigand, T., Supersymmetric (non-)Abelian bundles in the Type I and SO(32) heterotic string, JHEP, 08, 009 (2005)
[17] Blumenhagen, R.; Moster, S.; Weigand, T., Heterotic GUT and standard model vacua from simply connected Calabi-Yau manifolds, Nucl. Phys., B 751, 186 (2006) · Zbl 1192.81257
[18] Blumenhagen, R.; Moster, S.; Reinbacher, R.; Weigand, T., Massless spectra of three generation U(N ) heterotic string vacua, JHEP, 05, 041 (2007)
[19] Otsuka, H.; Takemoto, K., SO(32) heterotic standard model vacua in general Calabi-Yau compactifications, JHEP, 11, 034 (2018) · Zbl 1404.83123
[20] Hinton, GE; Salakhutdinov, RR, Reducing the dimensionality of data with neural networks, Science, 313, 504 (2006) · Zbl 1226.68083
[21] Candelas, P.; Dale, AM; Lütken, CA; Schimmrigk, R., Complete intersection Calabi-Yau manifolds, Nucl. Phys., B 298, 493 (1988)
[22] P. Candelas, C.A. Lütken and R. Schimmrigk, Complete intersection Calabi-Yau manifolds. 2. Three generation manifolds, Nucl. Phys.B 306 (1988) 113 [INSPIRE].
[23] A. Lukas et al., http://www-thphys.physics.ox.ac.uk/projects/CalabiYau/cicylist/cicylist.txt.
[24] D. Arthur and S. Vassilvitskii, k-means++: the advantages of careful seeding, in the proceedings of the 18^thannual ACM-SIAM symposium on Discrete algorithms, January 7-9, New Orleans, U.S.A. (2007). · Zbl 1302.68273
[25] Kullback, S.; Leibler, RA, On information and sufficiency, Ann. Math. Statist., 22, 79 (1951) · Zbl 0042.38403
[26] Anderson, LB; Gray, J.; Lukas, A.; Palti, E., Two hundred heterotic standard models on smooth Calabi-Yau threefolds, Phys. Rev., D 84, 106005 (2011)
[27] Anderson, LB; Gray, J.; Lukas, A.; Palti, E., Heterotic line bundle standard models, JHEP, 06, 113 (2012) · Zbl 1397.81406
[28] Abe, H.; Kobayashi, T.; Otsuka, H.; Takano, Y., Realistic three-generation models from SO(32) heterotic string theory, JHEP, 09, 056 (2015) · Zbl 1388.81747
[29] Otsuka, H., SO(32) heterotic line bundle models, JHEP, 05, 045 (2018) · Zbl 1391.83117
[30] Witten, E., D-branes and k-theory, JHEP, 12, 019 (1998) · Zbl 0959.81070
[31] Uranga, AM, D-brane probes, RR tadpole cancellation and k-theory charge, Nucl. Phys., B 598, 225 (2001) · Zbl 1046.81543
[32] Braun, V., On free quotients of complete intersection Calabi-Yau manifolds, JHEP, 04, 005 (2011) · Zbl 1250.14026
[33] Davis, M., Hilbert’s tenth problem is unsolvable, Amer. Math. Mon., 80, 233 (1973) · Zbl 0277.02008
[34] M. Abadi et al., TensorFlow: large-scale machine learning on heterogeneous distributed systems, arXiv:1603.04467 [INSPIRE].
[35] Pedregosa, F., Scikit-learn: machine learning in Python, J. Machine Learning Res., 12, 2825 (2011) · Zbl 1280.68189
[36] Kanno, H., A note on higher dimensional instantons and supersymmetric cycles, Prog. Theor. Phys. Suppl., 135, 18 (1999)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.