# Asymptotic Optimality for Decentralised Bandits

arXiv: https://arxiv.org/abs/2109.09427 · HTML: https://mlsanity.com/paper/2109.09427/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 20 Sep 2021.

## Builds on (most cited first, 6 of 6)

- [Social Learning in Multi Agent Multi Armed Bandits](https://mlsanity.com/paper/1910.02100/) (2019)
- [The Gossiping Insert-Eliminate Algorithm for Multi-Agent Bandits](https://mlsanity.com/paper/2001.05452/) (2020)
- [Cooperative Multi-Agent Bandits with Heavy Tails](https://mlsanity.com/paper/2008.06244/) (2020)
- [Collaborative Learning of Stochastic Bandits over a Social Network](https://mlsanity.com/paper/1602.08886/) (2016)
- [Multi-Agent Multi-Armed Bandits with Limited Communication](https://mlsanity.com/paper/2102.08462/) (2021)
- [Cooperative Online Learning: Keeping your Neighbors Updated](https://mlsanity.com/paper/1901.08082/) (2019)

## Built on by (most cited first, 2 of 2)

- [Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits](https://mlsanity.com/paper/2305.18784/) (2023)
- [Distributed No-Regret Learning for Multi-Stage Systems with End-to-End Bandit Feedback](https://mlsanity.com/paper/2404.04509/) (2024)

## Abstract (arXiv)

We consider a large number of agents collaborating on a multi-armed bandit problem with a large number of arms. The goal is to minimise the regret of each agent in a communication-constrained setting. We present a decentralised algorithm which builds upon and improves the Gossip-Insert-Eliminate method of Chawla et al. arxiv:2001.05452. We provide a theoretical analysis of the regret incurred which shows that our algorithm is asymptotically optimal. In fact, our regret guarantee matches the asymptotically optimal rate achievable in the full communication setting. Finally, we present empirical results which support our conclusions