vix.ing · top · new · best · stats · spec

Distributed Clustering of Linear Bandits in Peer to Peer Networks

2016/04/26 by Nathan Korda, Korda, Nathan, Balázs Szörényi +3 · 4 citations
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Artificial Intelligence (cs.AI) #Data Stream Mining Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.1604.07706

openalex publication_date 2016/04/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We provide two distributed confidence ball algorithms for solving linear bandit problems in peer to peer networks with limited communication capabilities. For the first, we assume that all the peers are solving the same linear bandit problem, and prove that our algorithm achieves the optimal asymptotic regret rate of any centralised algorithm that can instantly communicate information between the peers. For the second, we assume that there are clusters of peers solving the same bandit problem within each cluster, and we prove that our algorithm discovers these clusters, while achieving the optimal asymptotic regret rate within each one. Through experiments on several real-world datasets, we demonstrate the performance of proposed algorithms compared to the state-of-the-art.

Citations

Cited by

Related