Rademacher Complexity and Structural Risk Minimization: an Application to Human Gene Expression Datasets

In this paper, we target the problem of model selection for Support Vector Classifiers through in–sample methods, which are partic- ularly appealing in the small–sample regime, i.e. when few high–dimen- sional patterns are available. In particular, we describe the application of a trimmed hinge loss function to Rademacher Complexity and Max- imal Discrepancy based in–sample approaches. We also show that the selected classifiers outperform the ones obtained with other state-of-the- art in-sample and out–of–sample model selection techniques in classifying Human Gene Expression datasets.