Thompson Sampling under Bernoulli Rewards with Local Differential Privacy

07/03/2023
by   Bo Jiang, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset