A Stochastic View of Optimal Regret through Minimax Duality

Details A Stochastic View of Optimal Regret through Minimax Duality A Stochastic View of Optimal Regret through Minimax Duality

2009-03-30

arxiv.org/abs/0903.5328v1

Computer Science

Learning

Scientific paper

We study the regret of optimal strategies for online convex optimization games. Using von Neumann's minimax theorem, we show that the optimal regret in this adversarial setting is closely related to the behavior of the empirical minimization algorithm in a stochastic process setting: it is equal to the maximum, over joint distributions of the adversary's action sequence, of the difference between a sum of minimal expected losses and the minimal empirical loss. We show that the optimal regret has a natural geometric interpretation, since it can be viewed as the gap in Jensen's inequality for a concave functional--the minimizer over the player's actions of expected loss--defined on a set of probability distributions. We use this expression to obtain upper and lower bounds on the regret of an optimal strategy for a variety of online learning problems. Our method provides upper bounds without the need to construct a learning algorithm; the lower bounds provide explicit optimal strategies for the adversary.

Affiliated with

Also associated with

No associations

Rating

A Stochastic View of Optimal Regret through Minimax Duality does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A Stochastic View of Optimal Regret through Minimax Duality, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Stochastic View of Optimal Regret through Minimax Duality will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-19784