Timezone: »

On the Universality of Online Mirror Descent
Nati Srebro · Karthik Sridharan · Ambuj Tewari

Tue Dec 13 08:45 AM -- 02:59 PM (PST) @ None #None

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

Author Information

Nati Srebro (TTI-Chicago)
Karthik Sridharan (University of Pennsylvania)
Ambuj Tewari (University of Michigan)

More from the Same Authors