Algorithms for Differentially Private ...
Type de document :
Communication dans un congrès avec actes
Titre :
Algorithms for Differentially Private Multi-Armed Bandits
Auteur(s) :
Tossou, Aristide [Auteur]
Dimitrakakis, Christos [Auteur]
Sequential Learning [SEQUEL]
Université de Lille, Sciences Humaines et Sociales
Dimitrakakis, Christos [Auteur]
Sequential Learning [SEQUEL]
Université de Lille, Sciences Humaines et Sociales
Titre de la manifestation scientifique :
AAAI 2016
Ville :
Phoenix, Arizona
Pays :
Etats-Unis d'Amérique
Date de début de la manifestation scientifique :
2016-02-11
Mot(s)-clé(s) en anglais :
differential privacy
regret
reinforcement learning
stochastic multi-armed bandits
regret
reinforcement learning
stochastic multi-armed bandits
Discipline(s) HAL :
Statistiques [stat]/Machine Learning [stat.ML]
Informatique [cs]/Cryptographie et sécurité [cs.CR]
Informatique [cs]/Cryptographie et sécurité [cs.CR]
Résumé en anglais : [en]
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 ...
Lire la suite >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 $(\epsilon, \delta)$ differentially private variants of Upper Confidence Bound algorithms which have optimal regret, $O(\epsilon^{-1} + \log T)$. This is a significant improvement over previous results, which only achieve poly-log regret $O(\epsilon^{-2} \log^{2} T)$, 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.Lire moins >
Lire la suite >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 $(\epsilon, \delta)$ differentially private variants of Upper Confidence Bound algorithms which have optimal regret, $O(\epsilon^{-1} + \log T)$. This is a significant improvement over previous results, which only achieve poly-log regret $O(\epsilon^{-2} \log^{2} T)$, 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.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- https://hal.inria.fr/hal-01234427/document
- Accès libre
- Accéder au document
- http://arxiv.org/pdf/1511.08681
- Accès libre
- Accéder au document
- https://hal.inria.fr/hal-01234427/document
- Accès libre
- Accéder au document
- https://hal.inria.fr/hal-01234427/document
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- 1511.08681
- Accès libre
- Accéder au document
- single-mab-aaai16-final.pdf
- Accès libre
- Accéder au document