On Differentially Private Federated Linear Contextual Bandits

Abstract: We consider cross-silo federated linear contextual bandit (LCB) problem under differential privacy, where multiple silos (agents) interact with the local users and communicate via a central server to realize collaboration while without sacrificing each user’s privacy. We identify three issues in the state-of-the-art: (i) failure of claimed privacy protection and (ii) incorrect regret bound due to noise miscalculation and (iii) ungrounded communication cost. To resolve these issues, we take a two-step principled approach. First, we design an algorithmic framework consisting of a generic federated LCB algorithm and flexible privacy protocols. Then, leveraging the proposed framework, we study federated LCBs under two different privacy constraints. We first establish privacy and regret guarantees under silo-level local differential privacy, which fix the issues present in state-of-the-art algorithm. To further improve the regret performance, we next consider shuffle model of differential privacy, under which we show that our algorithm can achieve nearly “optimal” regret without a trusted server. We accomplish this via two different schemes – one relies on a new result on privacy amplification via shuffling for DP mechanisms and another one leverages the integration of a shuffle protocol for vector sum into the tree-based mechanism, both of which might be of independent interest. Finally, we support our theoretical results with numerical evaluations over contextual bandit instances generated from both synthetic and real-life data.

Bio: Xingyu Zhou is currently an Assistant Professor at ECE of Wayne State University. He received his Ph.D. from Ohio State University (advised by Ness Shroff), his master’s and bachelor’s degrees from Tsinghua University, and BUPT (all with the highest honors). His research interest includes machine learning (e.g., bandits, reinforcement learning), stochastic systems, and applied probability (e.g., load balancing). Currently, he is particularly interested in online decision-making with formal privacy guarantees. His research has not only led to several invited talks at Caltech, CMU, and UCLA, but won Best Student Paper Award and Runner-up at WiOpt 2022. He is also the recipient of various awards, including the NSF CRII award, the Presidential Fellowship at OSU, the Outstanding Graduate Award of Beijing city, the National Scholarship of China, the Academic Rising Star Award at Tsinghua University, and the Dec. 9th Scholarship of Tsinghua University. He has served as a TPC for conferences including Sigmetrics, MobiHoc, INFOCOM etc.