2026-09-19T17:15:13Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1236362021-07-05T14:03:20Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Alex P. Pentland. Dubey, Abhimanyu. Program in Media Arts and Sciences (Massachusetts Institute of Technology) Program in Media Arts and Sciences (Massachusetts Institute of Technology) 2020-01-23T17:01:54Z 2020-01-23T17:01:54Z 2019 2019 https://hdl.handle.net/1721.1/123636 1136490586 Thesis: S.M., Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2019 Cataloged from PDF version of thesis. Includes bibliographical references (pages 99-106). In this thesis, I consider the research problem of designing optimal algorithms for two specific settings of the stochastic multi-armed bandit problem. The first setting considers the problem where rewards are drawn from a family of extremely heavy-tailed distributions known as a-stable distributions. For this setting, I extended an existing upper confidence bound algorithm, to create an optimal frequentist algorithm, titled [alpha]-UCB. Next, I developed a variant of the Bayesian Thompson Sampling algorithm in this setting, titled Robust [alpha]-TS, which involved developing an efficient pipeline for posterior inference. I also proved finite-time regret bounds for this algorithm, that are optimal up to logarithmic factors. The second problem setting I considered was the networked multi-agent problem where agents have local communication, and have unique preferences. This problem setting is a generalization of the co-operative multi-agent stochastic bandit problem, and is a closely related variant of the single-agent bandit setting with side observations. For this setting, I developed an optimal upper confidence bound algorithm, titled Net-UCB. I also proved finite-time regret bounds for this algorithm that are logarithmic in the number of rounds, and are sub-linear in the number of agents. For both settings, I conducted extensive experiments to verify the tightness of the regret bounds established, and compare performance with existing state-of-the-art algorithms. The algorithms proposed in this thesis obtain competitive regret and state-of-the-art performance across a variety of problem settings. by Abhimanyu Dubey. S.M. S.M. Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences 106 pages eng Massachusetts Institute of Technology MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 Program in Media Arts and Sciences Robust sequential decision-making on networks Thesis application/pdf 2020-01-23T17:01:53Z Publication Master Media unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="2d326947-51ed-44ab-908d-67a8faaaef49"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Robust sequential decision-making on networks</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2019</PublicationDate> <Authors> <Author> <DisplayName>Dubey, Abhimanyu.</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Program in Media Arts and Sciences</Keyword> <Abstract>In this thesis, I consider the research problem of designing optimal algorithms for two specific settings of the stochastic multi-armed bandit problem. The first setting considers the problem where rewards are drawn from a family of extremely heavy-tailed distributions known as a-stable distributions. For this setting, I extended an existing upper confidence bound algorithm, to create an optimal frequentist algorithm, titled [alpha]-UCB. Next, I developed a variant of the Bayesian Thompson Sampling algorithm in this setting, titled Robust [alpha]-TS, which involved developing an efficient pipeline for posterior inference. I also proved finite-time regret bounds for this algorithm, that are optimal up to logarithmic factors. The second problem setting I considered was the networked multi-agent problem where agents have local communication, and have unique preferences. This problem setting is a generalization of the co-operative multi-agent stochastic bandit problem, and is a closely related variant of the single-agent bandit setting with side observations. For this setting, I developed an optimal upper confidence bound algorithm, titled Net-UCB. I also proved finite-time regret bounds for this algorithm that are logarithmic in the number of rounds, and are sub-linear in the number of agents. For both settings, I conducted extensive experiments to verify the tightness of the regret bounds established, and compare performance with existing state-of-the-art algorithms. The algorithms proposed in this thesis obtain competitive regret and state-of-the-art performance across a variety of problem settings.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>