In this paper we are interested in what we term the federated private bandits framework, that combines differential privacy with multi-agent bandit learning. We explore how differential privacy based Upper Confidence Bound (UCB) methods can be applied to multi-agent environments, and in particular to federated learning environments both in ‘master-worker’ and ‘fully decentralized’ settings. We provide a theoretical analysis on the privacy and regret performance of the proposed methods and explore the tradeoffs between these two.


Tan Li

City University of Hong Kong

Linqi Song

City University of Hong Kong

Session Chair

Changho Suh

Korea Advanced Institute of Science and Technology