×

Semi-supervised logistic discrimination via regularized Gaussian basis expansions. (English) Zbl 1217.62090

Summary: The problem of constructing classification methods based on both labeled and unlabeled data sets is considered for analyzing data with complex structure. We introduce a semi-supervised logistic discriminant model with Gaussian basis expansions. Unknown parameters included in the logistic model are estimated by regularization method along with the technique of EM algorithm. For selection of adjusted parameters, we derive a model selection criterion from Bayesian viewpoints. Numerical studies are conducted to investigate the effectiveness of our proposed modeling procedures.

MSC:

62H30 Classification and discrimination; cluster analysis (statistical aspects)
62G08 Nonparametric regression and quantile regression
62F15 Bayesian inference
65C60 Computational problems in statistics (MSC2010)

Software:

PRMLT
PDFBibTeX XMLCite
Full Text: DOI Link

References:

[1] Amini , M.R. , Gallinari , P. ( 2002 ). Semi-supervised logistic regression.Proc. 15th Euro. Conf. Artif. Intell.390–394 .
[2] DOI: 10.1007/s10463-007-0143-3 · Zbl 1332.62198 · doi:10.1007/s10463-007-0143-3
[3] Bennett K. P., Adv. Neur. Inform. Process. Syst. 11 pp 368– (1998)
[4] Bennett , K. P. , Demiriz , A. , Maclin , R. ( 2002 ). Exploiting unlabeled data in ensemble methods.Proc. ACM Int. Conf. Knowledge Discov. Data Mining, pp. 289–296 .
[5] Bishop C. M., Pattern Recognition and Machine Learning (2006) · Zbl 1107.68072
[6] Chapelle O., Semi-Supervised Learning (2006)
[7] Chen K., Adv. Neur. Inform. Process. Syst. 20 pp 281– (2007)
[8] DOI: 10.1111/j.1467-9876.2005.00526.x · Zbl 1490.62155 · doi:10.1111/j.1467-9876.2005.00526.x
[9] Dempster A. P., J. Roy. Statist. Soc. B 39 pp 1– (1977)
[10] Green P. J., Nonparametric Regression and Generalized Linear Models (1994) · Zbl 0832.62032
[11] DOI: 10.1007/978-0-387-84858-7 · Zbl 1273.62005 · doi:10.1007/978-0-387-84858-7
[12] Kai , Y. , Tresp , V. , Zhou , D. ( 2004 ). Semi-supervised induction with basis functions. Technical Report. Department of Empirical Inference, Max Planck Institute for Biological Cybernetics, Tuebingen, Germany .
[13] DOI: 10.1093/biomet/91.1.27 · Zbl 1132.62313 · doi:10.1093/biomet/91.1.27
[14] DOI: 10.1007/978-0-387-71887-3 · doi:10.1007/978-0-387-71887-3
[15] DOI: 10.1109/5.726791 · doi:10.1109/5.726791
[16] DOI: 10.1214/088342307000000032 · Zbl 1246.62157 · doi:10.1214/088342307000000032
[17] Miller D., Adv. Neur. Inform. Proces. Syst. 9 pp 571– (1997)
[18] DOI: 10.1162/neco.1989.1.2.281 · doi:10.1162/neco.1989.1.2.281
[19] DOI: 10.1214/aos/1176344136 · Zbl 0379.62005 · doi:10.1214/aos/1176344136
[20] Sigillito V. G., Johns Hopkins APL Techn. Dig. 10 pp 262– (1989)
[21] DOI: 10.2307/2287970 · Zbl 0587.62067 · doi:10.2307/2287970
[22] Vapnik V., Statistical Learning Theory (1998) · Zbl 0935.62007
[23] Vittaut , J.N. , Amini , M.R. , Gallinari , P. ( 2002 ). Learning classification with both labeled and unlabeled data.Proc. 13th Eur. Conf. Mach. Learn.468–479 . · Zbl 1014.68516
[24] Zhou D., Adv. Neur. Inform. Process. Syst. 16 pp 321– (2004)
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. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.