Pure Exploration in Asynchronous Federated Bandits

Zichen Wang, Chuanhao Li, chenyu song, Lianghui Wang, Quanquan Gu, Huazheng Wang

Keywords: Bandits; Federated learning; Pure exploration

TL;DR: We propose the first federated asynchronous multi-armed bandit and linear bandit algorithms for pure exploration with fixed confidence.

Abstract: We study the federated pure exploration problem of multi-armed bandits and linear bandits, where $M$ agents cooperatively identify the best arm via communicating with the central server. To enhance the robustness against latency and unavailability of agents that are common in practice, we propose the first federated asynchronous multi-armed bandit and linear bandit algorithms for pure exploration with fixed confidence. Our theoretical analysis shows the proposed algorithms achieve near-optimal sample complexities and efficient communication costs in a fully asynchronous environment. Moreover, experimental results based on synthetic and real-world data empirically elucidate the effectiveness and communication cost-efficiency of the proposed algorithms.

List Of Authors: Zichen, Wang and Chuanhao, Li and Chenyu, Song and Lianghui, Wang and Quanquan, Gu and Huazheng, Wang

Submission Number: 308