A Reduction Principle for Generalizing Bona Fide Risk Bounds in Multi-class Setting

About this video

Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video

Reduction principle for generalizing risk bounds in multi-class settings. Teaches theoretical framework for extending binary classification results.

Video by Microsoft Research, played through YouTube's embedded player.

Part of Workshop on Extreme Classification at NIPS 2017