On the Universality of Online Mirror Descent

Part of Advances in Neural Information Processing Systems 24 (NIPS 2011)

Bibtex Metadata Paper Supplemental

Authors

Nati Srebro, Karthik Sridharan, Ambuj Tewari

Abstract

We show that for a general class of convex online learning problems, Mirror Descent can always achieve a (nearly) optimal regret guarantee.