Feature Selection and Dualities in Maximum Entropy Discrimination

TL;DR

This paper extends the maximum entropy discrimination framework to include feature selection, demonstrating improved classification/regression accuracy and discussing extensions for dealing with unobserved degrees of freedom.

Contribution

It formalizes feature selection within MED, a flexible Bayesian regularization approach, and shows practical improvements in linear classification/regression.

Findings

Substantial accuracy improvements in practice

Effective feature selection integrated into MED

Extensions for handling unobserved degrees of freedom

Abstract

Incorporating feature selection into a classification or regression method often carries a number of advantages. In this paper we formalize feature selection specifically from a discriminative perspective of improving classification/regression accuracy. The feature selection method is developed as an extension to the recently proposed maximum entropy discrimination (MED) framework. We describe MED as a flexible (Bayesian) regularization approach that subsumes, e.g., support vector classification, regression and exponential family models. For brevity, we restrict ourselves primarily to feature selection in the context of linear classification/regression methods and demonstrate that the proposed approach indeed carries substantial improvements in practice. Moreover, we discuss and develop various extensions of feature selection, including the problem of dealing with example specific but unobserved degrees of freedom -- alignments or invariants.