On Generalizing the C-Bound to the Multiclass and Multi-label Settings
arXiv:1501.03001
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.
NIPS 2014 Workshop on Representation and Learning Methods for Complex Outputs, Dec 2014, Montr{é}al, Canada