AAAI 2024technical4 citations
Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits
Abstract
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.
BibTeX
@article{Karpov_Zhang_2024, title={Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/29206}, DOI={10.1609/aaai.v38i12.29206}, abstractNote={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.}, number={12}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Karpov, Nikolai and Zhang, Qin}, year={2024}, month={Mar.}, pages={13076-13084} }