Federated Best Arm Identification With Heterogeneous Clients

• Published in: IEEE transactions on information theory Vol. 70; no. 6; pp. 4258 - 4279
• Main Authors: Chen, Zhirui, Karthik, P. N., Tan, Vincent Y. F., Chee, Yeow Meng
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Asymptotic properties; best arm identification; Clients; Costs; Error probability; federated learning; Lower bounds; Multi-armed bandits; Optimization; Servers; Surveys; Upper bound; Upper bounds; Voting

We study best arm identification in a federated multi-armed bandit setting with a central server and multiple clients, when each client has access to a subset of arms and each arm yields independent Gaussian observations. The goal is to identify the best arm of each client subject to an upper bound...