{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/123636"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/123636","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Robust sequential decision-making on networks","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_html":"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_has_math":false,"creators":["Dubey, Abhimanyu."],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Program in Media Arts and Sciences (Massachusetts Institute of Technology)","school":null,"contributors":[],"advisors":["Alex P. Pentland."],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019","date_published":"2019","updated_at":"2026-07-22T22:21:04Z","subjects":["Program in Media Arts and Sciences"],"languages":["eng"],"rights":["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."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/123636","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Alex P. Pentland."]},{"key":"dc:contributor.department","label":"Department","values":["Program in Media Arts and Sciences (Massachusetts Institute of Technology)","Media"]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Program in Media Arts and Sciences (Massachusetts Institute of Technology)"]},{"key":"dc:creator","label":"Author","values":["Dubey, Abhimanyu."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-01-23T17:01:54Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-01-23T17:01:54Z"]},{"key":"dc:date.issued","label":"Date","values":["2019"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Program in Media Arts and Sciences"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["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."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/123636"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["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)."]},{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Robust sequential decision-making on networks"]}]}],"canonical_facts":{"dc:contributor.advisor":["Alex P. Pentland."],"dc:contributor.department":["Program in Media Arts and Sciences (Massachusetts Institute of Technology)","Media"],"dc:contributor.other":["Program in Media Arts and Sciences (Massachusetts Institute of Technology)"],"dc:creator":["Dubey, Abhimanyu."],"dc:date.accessioned":["2020-01-23T17:01:54Z"],"dc:date.available":["2020-01-23T17:01:54Z"],"dc:date.issued":["2019"],"dc:description":["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)."],"dc:description.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."],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/123636"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["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."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Program in Media Arts and Sciences"],"dc:title":["Robust sequential decision-making on networks"],"dc:type":["Thesis"],"thesis:degree_name":["Master"]},"updated_at":"2026-07-22T22:21:04Z"}