Thompson sampling for one-dimensional exponential family bandits - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

Thompson sampling for one-dimensional exponential family bandits

Rémi Munos
  • Function : Author
  • PersonId : 836863


Thompson Sampling has been demonstrated in many complex bandit models, however the theoretical guarantees available for the parametric multi-armed bandit are still limited to the Bernoulli case. Here we extend them by proving asymptotic optimality of the algorithm using the Jeffreys prior for 1-dimensional exponential family bandits. Our proof builds on previous work, but also makes extensive use of closed forms for Kullback-Leibler divergence and Fisher information (and thus Jeffreys prior) available in an exponential family. This allow us to give a finite time exponential concentration inequality for posterior distributions on exponential families that may be of interest in its own right. Moreover our analysis covers some distributions for which no optimistic algorithm has yet been proposed, including heavy-tailed exponential families.
Fichier principal
Vignette du fichier
nips13-TS.pdf (180 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00923683 , version 1 (03-01-2014)


  • HAL Id : hal-00923683 , version 1


Nathaniel Korda, Emilie Kaufmann, Rémi Munos. Thompson sampling for one-dimensional exponential family bandits. Advances in Neural Information Processing Systems, 2013, United States. ⟨hal-00923683⟩
324 View
162 Download


Gmail Facebook Twitter LinkedIn More