On the Consistency of Multiclass Classification Methods
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.
Cite
Text
Tewari and Bartlett. "On the Consistency of Multiclass Classification Methods." Journal of Machine Learning Research, 2007.Markdown
[Tewari and Bartlett. "On the Consistency of Multiclass Classification Methods." Journal of Machine Learning Research, 2007.](https://mlanthology.org/jmlr/2007/tewari2007jmlr-consistency/)BibTeX
@article{tewari2007jmlr-consistency,
title = {{On the Consistency of Multiclass Classification Methods}},
author = {Tewari, Ambuj and Bartlett, Peter L.},
journal = {Journal of Machine Learning Research},
year = {2007},
pages = {1007-1025},
volume = {8},
url = {https://mlanthology.org/jmlr/2007/tewari2007jmlr-consistency/}
}