Home Page

Papers

Submissions

News

Editorial Board

Proceedings

Open Source Software

Search

Statistics

Login

Frequently Asked Questions

Contact Us



RSS Feed

On the Consistency of Multiclass Classification Methods

Ambuj Tewari, Peter L. Bartlett; 8(36):1007−1025, 2007.

Abstract

Binary classification is a well studied special case of the classification problem. Statistical properties of binary classifiers, such as consistency, have been investigated in a variety of settings. Binary classification methods can be generalized in many ways to handle multiple classes. It turns out that one can lose consistency in generalizing a binary classification method to deal with multiple classes. We study a rich family of multiclass methods and provide a necessary and sufficient condition for their consistency. We illustrate our approach by applying it to some multiclass methods proposed in the literature.

[abs][pdf][bib]       
© JMLR 2007. (edit, beta)