2000 character limit reached
On the Universality of Online Mirror Descent
Published 20 Jul 2011 in cs.LG | (1107.4080v1)
Abstract: We show that for a general class of convex online learning problems, Mirror Descent can always achieve a (nearly) optimal regret guarantee.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.