Federated Linear Contextual Bandits with Heterogeneous Clients

arXiv:2403.00116v1 Announce Type: new
Abstract: The demand for collaborative and private bandit learning across multiple agents is surging due to the growing quantity of data generated from distributed systems. Federated bandit learning has emerged as a promising framework for private, efficient, and decentralized online learning. However, almost all previous works rely on strong assumptions of client homogeneity, i.e., all participating clients shall share the same bandit model; otherwise, they all would suffer linear regret. This greatly restricts the application of …

abstract agents arxiv collaborative cs.ai cs.lg data decentralized demand distributed distributed systems framework generated linear multiple online learning systems type