Federated Linear Contextual Bandits with User-level Differential Privacy. (arXiv:2306.05275v1 [cs.LG])

This paper studies federated linear contextual bandits under the notion of
user-level differential privacy (DP). We first introduce a unified federated
bandits framework that can accommodate various definitions of DP in the
sequential decision-making setting. We then formally introduce user-level
central DP (CDP) and local DP (LDP) in the federated bandits framework, and
investigate the fundamental trade-offs between the learning regrets and the
corresponding DP guarantees in a federated linear contextual bandits model. For
CDP, we propose a federated algorithm …

cdp decision differential privacy framework linear local making privacy studies under