Algorithms for Differentially Private Multi-Armed Bandits
Paper in proceedings, 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.

Author

Aristide Tossou

Chalmers, Computer Science and Engineering (Chalmers), Computing Science (Chalmers)

Christos Dimitrakakis

Chalmers, Computer Science and Engineering (Chalmers), Computing Science (Chalmers)

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

2087-2093

Areas of Advance

Information and Communication Technology

Subject Categories

Probability Theory and Statistics

Computer Science

ISBN

9781577357605