Timezone: »

Federated Linear Contextual Bandits
Ruiquan Huang · Weiqiang Wu · Jing Yang · Cong Shen

Fri Dec 10 08:30 AM -- 10:00 AM (PST) @
This paper presents a novel federated linear contextual bandits model, where individual clients face different $K$-armed stochastic bandits coupled through common global parameters. By leveraging the geometric structure of the linear rewards, a collaborative algorithm called Fed-PE is proposed to cope with the heterogeneity across clients without exchanging local feature vectors or raw data. Fed-PE relies on a novel multi-client G-optimal design, and achieves near-optimal regrets for both disjoint and shared parameter cases with logarithmic communication costs. In addition, a new concept called collinearly-dependent policies is introduced, based on which a tight minimax regret lower bound for the disjoint parameter case is derived. Experiments demonstrate the effectiveness of the proposed algorithms on both synthetic and real-world datasets.

Author Information

Ruiquan Huang (The Pennsylvania State University)
Weiqiang Wu (University of Maryland, College Park)
Jing Yang (Pennsylvania State University)
Cong Shen (University of Virginia)

More from the Same Authors