English

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

Machine Learning 2015-01-14 v1 Machine Learning

Abstract

The C-bound, introduced in Lacasse et al., 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.

Cite

@article{arxiv.1501.03001,
  title  = {On Generalizing the C-Bound to the Multiclass and Multi-label Settings},
  author = {Francois Laviolette and Emilie Morvant and Liva Ralaivola and Jean-Francis Roy},
  journal= {arXiv preprint arXiv:1501.03001},
  year   = {2015}
}

Comments

NIPS 2014 Workshop on Representation and Learning Methods for Complex Outputs, Dec 2014, Montr{\'e}al, Canada

R2 v1 2026-06-22T07:59:43.970Z