ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1105.5041
173
89
v1v2 (latest)

Lipschitz Bandits without the Lipschitz Constant

25 May 2011
Sébastien Bubeck
Gilles Stoltz
Jia Yuan Yu
ArXiv (abs)PDFHTML
Abstract

We consider the setting of stochastic bandit problems with a continuum of arms. We first point out that the strategies considered so far in the literature only provided theoretical guarantees of the form: given some tuning parameters, the regret is small with respect to a class of environments that depends on these parameters. This is however not the right perspective, as it is the strategy that should adapt to the specific bandit environment at hand, and not the other way round. Put differently, an adaptation issue is raised. We solve it for the special case of environments whose mean-payoff functions are globally Lipschitz. More precisely, we show that the minimax optimal orders of magnitude Ld/(d+2) T(d+1)/(d+2)L^{d/(d+2)} \, T^{(d+1)/(d+2)}Ld/(d+2)T(d+1)/(d+2) of the regret bound against an environment fff with Lipschitz constant LLL over TTT time instances can be achieved without knowing LLL or TTT in advance. This is in contrast to all previously known strategies, which require to some extent the knowledge of LLL to achieve this performance guarantee.

View on arXiv
Comments on this paper