Vignette d'image

Dimitrakakis, Christos

Nom
Dimitrakakis, Christos
Affiliation principale
Fonction
Professor
Email
christos.dimitrakakis@unine.ch
Identifiants
https://libra.unine.ch/handle/123456789/30936
_
0000-0002-5367-5189

Résultat de la recherche

Filtres

2
2
2
Réinitialiser les filtres

Paramètres

Voici les éléments 1 - 2 sur 2
  • Publication
    Accès libre
    Thompson Sampling For Stochastic Bandits with Graph Feedback
    (2017-01-16T10:52:51Z)
    Aristide C. Y. Tossou
    ;
    Dimitrakakis, Christos 
    ;
    Devdatt Dubhashi
    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.
  • Publication
    Accès libre
    Achieving Privacy in the Adversarial Multi-Armed Bandit
    (2017)
    Aristide C. Y. Tossou
    ;
    Dimitrakakis, Christos 
    In this paper, we improve the previously best known regret bound to achieve ϵ-differential privacy in oblivious adversarial bandits from O(T2/3/ϵ) to O(T−−√lnT/ϵ). This is achieved by combining a Laplace Mechanism with EXP3. We show that though EXP3 is already differentially private, it leaks a linear amount of information in T. However, we can improve this privacy by relying on its intrinsic exponential mechanism for selecting actions. This allows us to reach O(lnT−−−√)-DP, with a regret of O(T2/3) that holds against an adaptive adversary, an improvement from the best known of O(T3/4). This is done by using an algorithm that run EXP3 in a mini-batch loop. Finally, we run experiments that clearly demonstrate the validity of our theoretical analysis.