Thompson Sampling under Bernoulli Rewards with Local Differential Privacy

2023/07/03 by Jiang, Bo, Zhao, Tianchi, Li, Ming
#Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2307.00863

Abstract

This paper investigates the problem of regret minimization for multi-armed bandit (MAB) problems with local differential privacy (LDP) guarantee. Given a fixed privacy budget ε, we consider three privatizing mechanisms under Bernoulli scenario: linear, quadratic and exponential mechanisms. Under each mechanism, we derive stochastic regret bound for Thompson Sampling algorithm. Finally, we simulate to illustrate the convergence of different mechanisms under different privacy budgets.

Related

• Multi-Armed Bandits with Local Differential Privacy
• Optimal Regret of Bernoulli Bandits under Global Differential Privacy
• Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret
• Cascading Bandit under Differential Privacy
• Thompson Sampling Itself is Differentially Private