Minimax policies for combinatorial prediction games

  • Audibert J
  • Bubeck S
  • Lugosi G
  • 34

    Readers

    Mendeley users who have this article in their library.
  • 13

    Citations

    Citations of this article.

Abstract

We address the online linear optimization problem when the actions of the forecaster are represented by binary vectors. Our goal is to understand the magnitude of the minimax regret for the worst possible set of actions. We study the problem under three different assumptions for the feedback: full information, and the partial information models of the so-called "semi-bandit", and "bandit" problems. We consider both L∞-, and L2-type of restrictions for the losses assigned by the adversary. We formulate a general strategy using Bregman projections on top of a potential-based gradient descent, which generalizes the ones studied in the series of papers György et al. (2007); Dani et al. (2008); Abemethy et al. (2008); Cesa-Bianchi and Lugosi (2009); Helmbold and Warmuth (2009); Kooien et al. (2010); Uchiya et al. (2010); Kale et al. (2010) and Audibert and Bubeck (2010). We provide simple proofs that recover most of the previous results. We propose new upper bounds for the semi-bandit game. Moreover we derive lower bounds for all three feedback assumptions. With the only exception of the bandit game, the upper and lower bounds are tight, up to a constant factor. Finally, we answer a question asked by Kooien et al. (2010) by showing that the exponentially weighted average forecaster is suboptimal against L∞ adversaries. © 2011 J.-Y. Audibert, S. Bubeck & G. Lugosi.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

  • ISSN: 15337928
  • SCOPUS: 2-s2.0-84897474760
  • arXiv: 1105.4871
  • PUI: 372812352
  • SGR: 84897474760

Authors

  • Jean Yves Audibert

  • Sébastien Bubeck

  • Gábor Lugosi

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free