On Generalizing the C-Bound to the Multiclass and Multi-label Settings

Abstract

The C-bound, introduced in Lacasse et al. [1], gives a tight upper bound on the risk of a binary majority vote classifier. In this work, we present a first step towards extending this work to more complex outputs, by providing generalizations of the C-bound to the multiclass and multi-label settings.

Extracted Key Phrases

1 Figure or Table

Cite this paper

@article{Laviolette2015OnGT, title={On Generalizing the C-Bound to the Multiclass and Multi-label Settings}, author={François Laviolette and Emilie Morvant and Liva Ralaivola and Jean-Francis Roy}, journal={CoRR}, year={2015}, volume={abs/1501.03001} }