Private reinforcement learning with pac and regret guarantees
Motivated by high-stakes decision-making domains like personalized medicine where user
information is inherently sensitive, we design privacy preserving exploration policies for …
information is inherently sensitive, we design privacy preserving exploration policies for …
Optimal Learning Policies for Differential Privacy in Multi-armed Bandits
S Wang, J Zhu - Journal of Machine Learning Research, 2024 - jmlr.org
This paper studies the multi-armed bandit problem with a requirement of differential privacy
guarantee or global differential privacy guarantee. We first prove that, the lower bound for …
guarantee or global differential privacy guarantee. We first prove that, the lower bound for …