Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits
DOI:
https://doi.org/10.1609/aaai.v38i12.29206Keywords:
ML: Online Learning & Bandits, ML: Distributed Machine Learning & Federated LearningAbstract
In this paper, we study the collaborative learning model, which concerns the tradeoff between parallelism and communication overhead in multi-agent multi-armed bandits. For regret minimization in multi-armed bandits, we present the first set of tradeoffs between the number of rounds of communication between the agents and the regret of the collaborative learning process.Downloads
Published
2024-03-24
How to Cite
Karpov, N., & Zhang, Q. (2024). Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits. Proceedings of the AAAI Conference on Artificial Intelligence, 38(12), 13076-13084. https://doi.org/10.1609/aaai.v38i12.29206
Issue
Section
AAAI Technical Track on Machine Learning III