Skip to Main content Skip to Navigation
New interface
Preprints, Working Papers, ...

On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits

Abstract : We lay the foundations of a non-parametric theory of best-arm identification in multi-armed bandits with a fixed budget T. We consider general, possibly non-parametric, models D for distributions over the arms; an overarching example is the model D = P(0,1) of all probability distributions over [0,1]. We propose upper bounds on the average log-probability of misidentifying the optimal arm based on information-theoretic quantities that correspond to infima over Kullback-Leibler divergences between some distributions in D and a given distribution. This is made possible by a refined analysis of the successive-rejects strategy of Audibert, Bubeck, and Munos (2010). We finally provide lower bounds on the same average log-probability, also in terms of the same new information-theoretic quantities; these lower bounds are larger when the (natural) assumptions on the considered strategies are stronger. All these new upper and lower bounds generalize existing bounds based, e.g., on gaps between distributions.
Complete list of metadata
Contributor : Gilles Stoltz Connect in order to contact the contributor
Submitted on : Friday, September 30, 2022 - 12:28:57 PM
Last modification on : Thursday, November 3, 2022 - 9:39:50 AM


Files produced by the author(s)


  • HAL Id : hal-03792668, version 1
  • ARXIV : 2210.00895


Antoine Barrier, Aurélien Garivier, Gilles Stoltz. On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits. {date}. ⟨hal-03792668⟩



Record views


Files downloads