Learning Theory

Volume 3559 of the series Lecture Notes in Computer Science pp 143-157

On the Consistency of Multiclass Classification Methods

  • Ambuj TewariAffiliated withCarnegie Mellon UniversityDivision of Computer Science, University of California
  • , Peter L. BartlettAffiliated withCarnegie Mellon UniversityDivision of Computer Science and Department of Statistics, University of California

* Final gross prices may vary according to local VAT.

Get Access


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.