ML Anthology

On the Consistency of Multiclass Classification Methods

Ambuj Tewari, Peter L. Bartlett
COLT 2005 pp. 143-157
doi:10.1007/11503415_10 /colt/2005/tewari2005colt-consistency/

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.

PDF COLT Semantic Scholar

Cite

Text

Tewari and Bartlett. "On the Consistency of Multiclass Classification Methods." Annual Conference on Computational Learning Theory, 2005. doi:10.1007/11503415_10

Markdown

[Tewari and Bartlett. "On the Consistency of Multiclass Classification Methods." Annual Conference on Computational Learning Theory, 2005.](https://mlanthology.org/colt/2005/tewari2005colt-consistency/) doi:10.1007/11503415_10

BibTeX

@inproceedings{tewari2005colt-consistency,
  title     = {{On the Consistency of Multiclass Classification Methods}},
  author    = {Tewari, Ambuj and Bartlett, Peter L.},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2005},
  pages     = {143-157},
  doi       = {10.1007/11503415_10},
  url       = {https://mlanthology.org/colt/2005/tewari2005colt-consistency/}
}