Logo du site
  • English
  • Français
  • Se connecter
Logo du site
  • English
  • Français
  • Se connecter
  1. Accueil
  2. Université de Neuchâtel
  3. Publications
  4. Thompson Sampling For Stochastic Bandits with Graph Feedback
 
  • Details
Options
Vignette d'image

Thompson Sampling For Stochastic Bandits with Graph Feedback

Auteur(s)
Aristide C. Y. Tossou
Dimitrakakis, Christos 
Institut d'informatique 
Devdatt Dubhashi
Date de parution
2017-01-16T10:52:51Z
Mots-clés
  • Machine Learning (cs.LG)
  • Artificial Intelligence (cs.AI)
  • Machine Learning (cs....

  • Artificial Intelligen...

Résumé
We present a novel extension of Thompson Sampling for stochastic sequential decision problems with graph feedback, even when the graph structure itself is unknown and/or changing. We provide theoretical guarantees on the Bayesian regret of the algorithm, linking its performance to the underlying properties of the graph. Thompson Sampling has the advantage of being applicable without the need to construct complicated upper confidence bounds for different problems. We illustrate its performance through extensive experimental results on real and simulated networks with graph feedback. More specifically, we tested our algorithms on power law, planted partitions and Erdo's-Renyi graphs, as well as on graphs derived from Facebook and Flixster data. These all show that our algorithms clearly outperform related methods that employ upper confidence bounds, even if the latter use more information about the graph.
Identifiants
https://libra.unine.ch/handle/123456789/30952
_
1701.04238v1
Type de publication
conference paper
Dossier(s) à télécharger
 main article: 1701.04238.pdf (1.55 MB)
google-scholar
Présentation du portailGuide d'utilisationStratégie Open AccessDirective Open Access La recherche à l'UniNE Open Access ORCIDNouveautés

Service information scientifique & bibliothèques
Rue Emile-Argand 11
2000 Neuchâtel
contact.libra@unine.ch

Propulsé par DSpace, DSpace-CRIS & 4Science | v2022.02.00