Abstract : 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 one-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 (through the 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.
https://hal.telecom-paris.fr/hal-02288407
Contributor : Telecomparis Hal <>
Submitted on : Saturday, September 14, 2019 - 6:46:55 PM Last modification on : Tuesday, December 8, 2020 - 10:06:05 AM
Nathaniel Korda, Emilie Kaufmann, Rémi Munos. Thompson Sampling for one-dimensial exponential family bandits. NIPS 2013 - Neural Information Processing Systems Conference, Dec 2013, Lake Tahoe, United States. ⟨hal-02288407⟩