International Conference on Computational Learning Theory

COLT 2005: Learning Theory pp 143-157

On the Consistency of Multiclass Classification Methods

  • Ambuj Tewari
  • Peter L. Bartlett
Conference paper

DOI: 10.1007/11503415_10

Volume 3559 of the book series Lecture Notes in Computer Science (LNCS)
Cite this paper as:
Tewari A., Bartlett P.L. (2005) On the Consistency of Multiclass Classification Methods. In: Auer P., Meir R. (eds) Learning Theory. COLT 2005. Lecture Notes in Computer Science, vol 3559. Springer, Berlin, Heidelberg

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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Ambuj Tewari
    • 1
  • Peter L. Bartlett
    • 2
  1. 1.Division of Computer ScienceUniversity of CaliforniaBerkeley
  2. 2.Division of Computer Science and Department of StatisticsUniversity of CaliforniaBerkeley