The Feature Selection Path in Kernel Methods

Fuxin Li, Cristian Sminchisescu ; JMLR W&CP 9:445-452, 2010.

Abstract

The problem of automatic feature selection/weighting in kernel methods is examined. We work on a formulation that optimizes both the weights of features and the parameters of the kernel model simultaneously, using L_1 regularization for feature selection. Under quite general choices of kernels, we prove that there exists a unique regularization path for this problem, that runs from 0 to a stationary point of the non-regularized problem. We propose an ODE-based homotopy method to follow this trajectory. By following the path, our algorithm is able to automatically discard irrelevant features and to automatically go back and forth to avoid local optima. Experiments on synthetic and real datasets show that the method achieves low prediction error and is efficient in separating relevant from irrelevant features.



Home Page

Papers

Submissions

News

Scope

Editorial Board

Announcements

Proceedings

Open Source Software

Search

Login



RSS Feed

Page last modified on Wed Mar 24 15:36 GMT 2010.

Copyright @ JMLR 2000. All rights reserved.