Timezone: »

Optimization, Learning, and Games with Predictable Sequences
Sasha Rakhlin · Karthik Sridharan

Sun Dec 08 02:00 PM -- 06:00 PM (PST) @ Harrah's Special Events Center, 2nd Floor #None

We provide several applications of Optimistic Mirror Descent, an online learning algorithm based on the idea of predictable sequences. First, we recover the Mirror-Prox algorithm, prove an extension to Holder-smooth functions, and apply the results to saddle-point type problems. Second, we prove that a version of Optimistic Mirror Descent (which has a close relation to the Exponential Weights algorithm) can be used by two strongly-uncoupled players in a finite zero-sum matrix game to converge to the minimax equilibrium at the rate of O(log T / T). This addresses a question of Daskalakis et al, 2011. Further, we consider a partial information version of the problem. We then apply the results to approximate convex programming and show a simple algorithm for the approximate Max-Flow problem.

Author Information

Sasha Rakhlin (University of Pennsylvania)
Karthik Sridharan (University of Pennsylvania)

More from the Same Authors