Abstract
In this letter, we target the problem of model selection for support vector classifiers through in-sample methods, which are particularly appealing in the small-sample regime. In particular, we describe the application of a trimmed hinge loss function to the Rademacher complexity and maximal discrepancy-based in-sample approaches and show that the selected classifiers outperform the ones obtained with other in-sample model selection techniques, which exploit a soft loss function, in classifying microarray data.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Alon U, Barkai N, Notterman D, Gish K, Ybarra S, Mack D, Levine A (1999) Broad patterns of gene expression revealed by clustering analysis of tumor and normal colon tissues probed by oligonucleotide arrays. Proc Natl Acad Sci USA 96(12): 6745
Ancona N, Maglietta R, Piepoli A, D’Addabbo A, Cotugno R, Savino M, Liuni S, Carella M, Pesole G, Perri F (2006) On the statistical assessment of classifiers using dna microarray data. BMC Bioinform 7(1): 387
Anguita D, Ghio A, Greco N, Oneto L, Ridella S (2010) Model selection for support vector machines: advantages and disadvantages of the machine learning theory. In: Proceedings of the international joint conference on neural networks
Anguita D, Ghio A, Oneto L, Ridella S (2011a) In-sample model selection for support vector machines. In: Proceedings of the international joint conference on neural networks
Anguita D, Ghio A, Oneto L, Ridella S (2011b) Selecting the hypothesis space for improving the generalization ability of support vector machines. In: Proceedings of the international joint conference on neural networks
Anguita D, Ghio A, Ridella S (2011c) Maximal discrepancy for support vector machines. Neurocomputing 74: 1436–1443
Bartlett P, Boucheron S, Lugosi G (2002) Model selection and error estimation. Mach Learn 48: 85–113
Braga-Neto U, Dougherty E (2004) Is cross-validation valid for small-sample microarray classification?. Bioinformatics 20(3): 374
Collobert R, Sinz F, Weston J, Bottou L (2006) Trading convexity for scalability. In: Proceedings of the 23rd international conference on machine learning, pp 201–208
Duan K, Keerthi SS, Poo AN (2003) Evaluation of simple performance measures for tuning SVM hyperparameters. Neurocomputing 51: 41–59
Golub T, Slonim D, Tamayo P, Huard C, Gaasenbeek M, Mesirov J, Coller H, Loh M, Downing J, Caligiuri M et al (1999) Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. Science 286(5439): 531
Page D, Zhan F, Cussens J, Waddell M, Hardin J, Barlogie B, Shaughnessy Jr J (2002) Comparative data mining for microarrays: A case study based on multiple myeloma. In: Poster presentation at international conference on intelligent systems for molecular biology, August
Pelckmans K, Suykens J, De Moor B (2004) Morozov, Ivanov and Tikhonov regularization based LS-SVMs. Neural Inf Process 3316: 1216–1222
Platt J (1999) Sequential minimal optimization: a fast algorithm for training support vector machines. Adv Kernel Methods Support Vector Learn 208: 98–112
Shawe-Taylor J, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge University Press, Cambridge
Statnikov A, Aliferis C, Tsamardinos I, Hardin D, Levy S (2005a) A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis. Bioinformatics 21(5): 631
Statnikov A, Tsamardinos I, Dosbayev Y, Aliferis C (2005b) Gems: a system for automated cancer diagnosis and biomarker discovery from microarray gene expression data. Int J Med Inform 74(7–8): 491–503
Vapnik V (1998) Statistical learning theory. Wiley-Interscience, New York
West M, Blanchette C, Dressman H, Huang E, Ishida S, Spang R, Zuzan H, Olson J, Marks J, Nevins J (2001) Predicting the clinical status of human breast cancer by using gene expression profiles. Proc Natl Acad Sci USA 98(20): 11462
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Anguita, D., Ghio, A., Oneto, L. et al. In-sample Model Selection for Trimmed Hinge Loss Support Vector Machine. Neural Process Lett 36, 275–283 (2012). https://doi.org/10.1007/s11063-012-9235-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-012-9235-z