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

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