Skip to Main content Skip to Navigation
Conference papers

Gossip-based distributed stochastic bandit algorithms

Balázs Szorenyi 1, 2 Róbert Busa-Fekete 2, 3 Istvan Hegedüs 2 Róbert Ormandi 2 Márk Jelasity 2 Balázs Kégl 4, 5 
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
4 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
5 Appstat
LAL - Laboratoire de l'Accélérateur Linéaire, LRI - Laboratoire de Recherche en Informatique
Abstract : The multi-armed bandit problem has attracted remarkable attention in the machine learning community and many efficient algorithms have been proposed to handle the so-called exploitation-exploration dilemma in various bandit setups. At the same time, significantly less effort has been devoted to adapting bandit algorithms to particular architectures, such as sensor networks, multi-core machines, or peer-to-peer (P2P) environments, which could potentially speed up their convergence. Our goal is to adapt stochastic bandit algorithms to P2P networks. In our setup, the same set of arms is available in each peer. In every iteration each peer can pull one arm independently of the other peers, and then some limited communication is possible with a few random other peers. As our main result, we show that our adaptation achieves a linear speedup in terms of the number of peers participating in the network. More precisely, we show that the probability of playing a suboptimal arm at a peer in iteration t=Ω(logN) is proportional to 1/(Nt) where N denotes the number of peers. The theoretical results are supported by simulation experiments showing that our algorithm scales gracefully with the size of network.
Complete list of metadata

Cited literature [14 references]  Display  Hide  Download
Contributor : Sabine Starita Connect in order to contact the contributor
Submitted on : Thursday, November 21, 2013 - 11:23:05 AM
Last modification on : Sunday, June 26, 2022 - 12:00:09 PM
Long-term archiving on: : Saturday, February 22, 2014 - 4:33:40 AM


Publisher files allowed on an open archive


  • HAL Id : in2p3-00907406, version 1



Balázs Szorenyi, Róbert Busa-Fekete, Istvan Hegedüs, Róbert Ormandi, Márk Jelasity, et al.. Gossip-based distributed stochastic bandit algorithms. ICML 2013 - 30th International Conference on Machine Learning, Jun 2013, Atlanta, United States. pp.19-27. ⟨in2p3-00907406⟩



Record views


Files downloads