On the Consistency of Multiclass Classification Methods.

Ambuj Tewari, Peter L. BartlettJMLR 2007 · OpenReview

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.
BibTeX
@article{tewari2007consistency,
  author = {Ambuj Tewari and Peter L. Bartlett},
  title = {{On the Consistency of Multiclass Classification Methods.}},
  journal = {J. Mach. Learn. Res.},
  year = {2007},
  url = {https://openreview.net/forum?id=-zWjt1PqFw1e},
}

Loading related content...

Figure