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.

Cite

Text

Karpov and Zhang. "Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I12.29206

Markdown

[Karpov and Zhang. "Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/karpov2024aaai-communication/) doi:10.1609/AAAI.V38I12.29206

BibTeX

@inproceedings{karpov2024aaai-communication,
  title     = {{Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits}},
  author    = {Karpov, Nikolai and Zhang, Qin},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {13076-13084},
  doi       = {10.1609/AAAI.V38I12.29206},
  url       = {https://mlanthology.org/aaai/2024/karpov2024aaai-communication/}
}