On Generalizing the C-Bound to the Multiclass and Multi-label Settings
arXiv:1501.03001v14 citations
Originality Synthesis-oriented
AI Analysis
This work addresses a theoretical limitation in machine learning for researchers, but it is incremental as it builds directly on prior binary work.
The authors tackled the problem of extending the C-bound, a tight risk upper bound for binary majority vote classifiers, to multiclass and multi-label settings, presenting generalizations as a first step.
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.