Logo du site
  • English
  • Français
  • Se connecter
Logo du site
  • English
  • Français
  • Se connecter
  1. Accueil
  2. Université de Neuchâtel
  3. Publications
  4. Algorithms for Differentially Private Multi-Armed Bandits
 
  • Details
Options
Vignette d'image

Algorithms for Differentially Private Multi-Armed Bandits

Auteur(s)
Aristide Tossou
Dimitrakakis, Christos 
Institut d'informatique 
Date de parution
2016
In
30th AAAI 2016
De la page
2087
A la page
2093
Mots-clés
  • Machine Learning (stat.ML)
  • Cryptography and Security (cs.CR)
  • Machine Learning (cs.LG)
  • Machine Learning (sta...

  • Cryptography and Secu...

  • Machine Learning (cs....

Résumé
We present differentially private algorithms for the stochastic Multi-Armed Bandit (MAB) problem. This is a problem for applications such as adaptive clinical trials, experiment design, and user-targeted advertising where private information is connected to individual rewards. Our major contribution is to show that there exist (ϵ,δ) differentially private variants of Upper Confidence Bound algorithms which have optimal regret, O(ϵ−1+logT). This is a significant improvement over previous results, which only achieve poly-log regret O(ϵ−2log2T), because of our use of a novel interval-based mechanism. We also substantially improve the bounds of previous family of algorithms which use a continual release mechanism. Experiments clearly validate our theoretical bounds.
Nom de l'événement
30th AAAI 2016
Lieu
Phoenix, Arizona, USA
Identifiants
https://libra.unine.ch/handle/123456789/30976
Type de publication
conference paper
Dossier(s) à télécharger
 main article: 1511.08681.pdf (226.89 KB)
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