Nearly Uniform Validation Improves Compression-Based Error Bounds

Eric Bax; 9(Aug):1741--1755, 2008.

Abstract

This paper develops bounds on out-of-sample error rates for support vector machines (SVMs). The bounds are based on the numbers of support vectors in the SVMs rather than on VC dimension. The bounds developed here improve on support vector counting bounds derived using Littlestone and Warmuth's compression-based bounding technique.

[abs][pdf]




Home Page

Papers

Submissions

News

Editorial Board

Announcements

Proceedings

Open Source Software

Search

Statistics

Login

Contact Us



RSS Feed