Algorithms for Differentially Private Multi-Armed Bandits
Paper i proceeding, 2016

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.

Författare

Aristide Tossou

Chalmers, Data- och informationsteknik, Datavetenskap

Christos Dimitrakakis

Chalmers, Data- och informationsteknik, Datavetenskap

30th AAAI Conference on Artificial Intelligence, AAAI 2016, Phoenix Convention CenterPhoenix, United States, 12-17 February 2016

2087-2093

Styrkeområden

Informations- och kommunikationsteknik

Ämneskategorier

Sannolikhetsteori och statistik

Datavetenskap (datalogi)

ISBN

9781577357605