pith. sign in

arxiv: 1501.03001 · v1 · pith:SSBCUIIMnew · submitted 2015-01-13 · 📊 stat.ML · cs.LG

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

classification 📊 stat.ML cs.LG
keywords c-boundmulti-labelmulticlasssettingsworkbinaryboundclassifier
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.