Optimization, Learning, and Games With Predictable Sequences

Loading...
Thumbnail Image
Penn collection
Statistics Papers
Degree type
Discipline
Subject
Statistics and Probability
Theory and Algorithms
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Rakhlin, Alexander
Sridharan, Karthik
Contributor
Abstract

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 for offline optimization, prove an extension to Holder-smooth functions, and apply the results to saddle-point type problems. Next, 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 convex programming and exhibit a simple algorithm for the approximate Max Flow problem.

Advisor
Date of presentation
2013-01-01
Conference name
Statistics Papers
Conference dates
2023-05-17T15:29:44.000
Conference location
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Recommended citation
Collection