Communication-Efficient Collaborative Best Arm Identification

We investigate top-m arm identification, a basic problem in bandit theory, in a multi-agent learning model in which agents collaborate to learn an objective function. We are interested in designing collaborative learning algorithms that achieve maximum speedup (compared to single-agent learning algorithms) using minimum communication cost, as communication is frequently the bottleneck in multi-agent learning. We give both algorithmic and impossibility results, and conduct a set of experiments to demonstrate the effectiveness of our algorithms.

Authors

• Nikolai Karpov Indiana University
• Qin Zhang Shenzhen University

Keywords

• MAS: Agent Communication
• ML: Distributed Machine Learning & Federated Learning
• ML: Online Learning & Bandits