Work

Distributed Clustering of Linear Bandits in Peer to Peer Networks

Year: 2016

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1604.07706

Authors: Korda, Nathan, Szorenyi, Balazs, Li, Shuai

Institutions: University of Oxford, Technion – Israel Institute of Technology, MTA-SZTE Research Group on Artificial Intelligence, University of Insubria

Language: English

Topic: Advanced Bandit Algorithms Research

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: green

Funders: Hamad Bin Khalifa University, European Commission, Ministero dell’Istruzione, dell’Università e della Ricerca, Tsinghua University, Engineering and Physical Sciences Research Council, FP7 Ideas: European Research Council

Awards: G1184370674, G3207356259, G442989154, Scaling Up Reinforcement Learning: Structure Learning, Skill Acquisition, and Reward Shaping"", G896728979

OpenAlex ID: W2963335963

Cites: 21

Cited by: 101

Related to: 10