Learning the distribution with largest mean: two bandit frameworks

Abstract : Over the past few years, the multi-armed bandit model has become increasingly popular in the machine learning community, partly because of applications including online content optimization. This paper reviews two different sequential learning tasks that have been considered in the bandit literature ; they can be formulated as (sequentially) learning which distribution has the highest mean among a set of distributions, with some constraints on the learning process. For both of them (regret minimization and best arm identification) we present recent, asymptotically optimal algorithms. We compare the behaviors of the sampling rule of each algorithm as well as the complexity terms associated to each problem.
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01449822
Contributor : Emilie Kaufmann <>
Submitted on : Monday, November 6, 2017 - 5:02:22 PM
Last modification on : Monday, April 29, 2019 - 4:29:01 PM

Files

ESAIM17KG.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01449822, version 3
  • ARXIV : 1702.00001

Citation

Emilie Kaufmann, Aurélien Garivier. Learning the distribution with largest mean: two bandit frameworks. ESAIM: Proceedings and Surveys, EDP Sciences, In press, 2017, pp.1 - 10. ⟨hal-01449822v3⟩

Share

Metrics

Record views

247

Files downloads

208