Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits
Machine Learning
2023-12-22 v3
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 among the agents and the regret of the collaborative learning process.
Cite
@article{arxiv.2301.11442,
title = {Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits},
author = {Nikolai Karpov and Qin Zhang},
journal= {arXiv preprint arXiv:2301.11442},
year = {2023}
}
Comments
13 pages, 1 figure