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

Add code
Jan 13, 2015
Francois Laviolette, Emilie Morvant, Liva Ralaivola, Jean-Francis Roy
Figure 1 for On Generalizing the C-Bound to the Multiclass and Multi-label Settings

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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{\'e}al, Canada  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon