On the consistency of multiclass classification methods

Authors:
Ambuj Tewari;Peter L. Bartlett
Affiliations:
Division of Computer Science, University of California, Berkeley;Division of Computer Science and Department of Statistics, University of California, Berkeley
Venue:
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Year:
2005

Citing 4
Cited 3

Multicategory Classification by Support Vector Machines

Computational Optimization and Applications - Special issue on computational optimization—a tribute to Olvi Mangasarian, part I
On the algorithmic implementation of multiclass kernel-based vector machines

The Journal of Machine Learning Research
Statistical Analysis of Some Multi-Category Large Margin Classification Methods

The Journal of Machine Learning Research
Consistency of support vector machines and other regularized kernel classifiers

IEEE Transactions on Information Theory

Consistency of Multiclass Empirical Risk Minimization Methods Based on Convex Loss

The Journal of Machine Learning Research
Learning from Partial Labels

The Journal of Machine Learning Research
Subset ranking using regression

COLT'06 Proceedings of the 19th annual conference on Learning Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

Binary classification methods can be generalized in many ways to handle multiple classes. It turns out that not all generalizations preserve the nice property of Bayes consistency. We provide a necessary and sufficient condition for consistency which applies to a large class of multiclass classification methods. The approach is illustrated by applying it to some multiclass methods proposed in the literature.