Algorithms for Differentially Private Multi-Armed Bandits

11/27/2015
by   Aristide Tossou, et al.
0

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 + T). This is a significant improvement over previous results, which only achieve poly-log regret O(ϵ^-2^2 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/05/2021

Differentially Private Multi-Armed Bandits in the Shuffle Model

We give an (ε,δ)-differentially private algorithm for the multi-armed ba...
research
09/28/2018

Differentially Private Contextual Linear Bandits

We study the contextual linear bandit problem, a version of the standard...
research
01/16/2017

Achieving Privacy in the Adversarial Multi-Armed Bandit

In this paper, we improve the previously best known regret bound to achi...
research
02/19/2020

Propose, Test, Release: Differentially private estimation with high probability

We derive concentration inequalities for differentially private median a...
research
06/06/2018

Mitigating Bias in Adaptive Data Gathering via Differential Privacy

Data that is gathered adaptively --- via bandit algorithms, for example ...
research
10/24/2020

Federated Bandit: A Gossiping Approach

In this paper, we study Federated Bandit, a decentralized Multi-Armed Ba...
research
04/30/2018

Learning Optimal Reserve Price against Non-myopic Bidders

We consider the problem of learning optimal reserve price in repeated au...

Please sign up or login with your details

Forgot password? Click here to reset