{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/143222"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/143222","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Private and Provably Efficient Federated Decision-Making","abstract":"In this thesis, we study sequential multi-armed bandit and reinforcement learning in the federated setting, where a group of agents collaborates to improve their collective reward by communicating over a network. We first study the multi-armed bandit problem in a decentralized environment. We study federated bandit learning under several real-world environmental constraints, such as differentially private communication, heavy-tailed perturbations, and the presence of adversarial corruptions. For each of these constraints, we present algorithms with near-optimal regret guarantees and maintain competitive experimental performance on real-world networks. We characterize the asymptotic and minimax rates for these problems via network-dependent lower bounds as well. These algorithms provide substantial improvements over existing work in a variety of real-world and synthetic network topologies. Next, we study the contextual bandit problem in a federated learning setting with differential privacy. In this setting, we propose algorithms that match the optimal rate (up to poly-logarithmic terms) with only a logarithmic communication budget. We extend our approach to heterogeneous federated learning via a kernel-based approach, and also provide a no-regret algorithm for private Gaussian process bandit optimization. Finally, we study reinforcement learning in both the multi-agent and federated setting with linear function approximation. We propose variants of least-squares value iteration algorithms that are provably no-regret with only a constant communication budget. We believe that the future of machine learning entails large-scale cooperation between various data-driven entities, and this work will be beneficial to the development of reliable, scalable, and secure decision-making systems.","abstract_html":"In this thesis, we study sequential multi-armed bandit and reinforcement learning in the federated setting, where a group of agents collaborates to improve their collective reward by communicating over a network. We first study the multi-armed bandit problem in a decentralized environment. We study federated bandit learning under several real-world environmental constraints, such as differentially private communication, heavy-tailed perturbations, and the presence of adversarial corruptions. For each of these constraints, we present algorithms with near-optimal regret guarantees and maintain competitive experimental performance on real-world networks. We characterize the asymptotic and minimax rates for these problems via network-dependent lower bounds as well. These algorithms provide substantial improvements over existing work in a variety of real-world and synthetic network topologies. Next, we study the contextual bandit problem in a federated learning setting with differential privacy. In this setting, we propose algorithms that match the optimal rate (up to poly-logarithmic terms) with only a logarithmic communication budget. We extend our approach to heterogeneous federated learning via a kernel-based approach, and also provide a no-regret algorithm for private Gaussian process bandit optimization. Finally, we study reinforcement learning in both the multi-agent and federated setting with linear function approximation. We propose variants of least-squares value iteration algorithms that are provably no-regret with only a constant communication budget. We believe that the future of machine learning entails large-scale cooperation between various data-driven entities, and this work will be beneficial to the development of reliable, scalable, and secure decision-making systems.","abstract_has_math":false,"creators":["Dubey, Abhimanyu"],"institution":"Massachusetts Institute of Technology","degree_name":"Doctoral","degree_level":null,"degree_discipline":null,"degree_department":"Program in Media Arts and Sciences (Massachusetts Institute of Technology)","school":null,"contributors":[],"advisors":["Pentland, Alex P."],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-02","date_published":"2022-02","updated_at":"2026-07-22T22:21:53Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/143222","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Pentland, Alex P."]},{"key":"dc:contributor.department","label":"Department","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":["2022-06-15T13:04:38Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-06-15T13:04:38Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-02"]},{"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":["Doctoral","Doctor of Philosophy"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/143222"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In this thesis, we study sequential multi-armed bandit and reinforcement learning in the federated setting, where a group of agents collaborates to improve their collective reward by communicating over a network. We first study the multi-armed bandit problem in a decentralized environment. We study federated bandit learning under several real-world environmental constraints, such as differentially private communication, heavy-tailed perturbations, and the presence of adversarial corruptions. For each of these constraints, we present algorithms with near-optimal regret guarantees and maintain competitive experimental performance on real-world networks. We characterize the asymptotic and minimax rates for these problems via network-dependent lower bounds as well. These algorithms provide substantial improvements over existing work in a variety of real-world and synthetic network topologies. Next, we study the contextual bandit problem in a federated learning setting with differential privacy. In this setting, we propose algorithms that match the optimal rate (up to poly-logarithmic terms) with only a logarithmic communication budget. We extend our approach to heterogeneous federated learning via a kernel-based approach, and also provide a no-regret algorithm for private Gaussian process bandit optimization. Finally, we study reinforcement learning in both the multi-agent and federated setting with linear function approximation. We propose variants of least-squares value iteration algorithms that are provably no-regret with only a constant communication budget. We believe that the future of machine learning entails large-scale cooperation between various data-driven entities, and this work will be beneficial to the development of reliable, scalable, and secure decision-making systems."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:title","label":"Title","values":["Private and Provably Efficient Federated Decision-Making"]}]}],"canonical_facts":{"dc:contributor.advisor":["Pentland, Alex P."],"dc:contributor.department":["Program in Media Arts and Sciences (Massachusetts Institute of Technology)"],"dc:creator":["Dubey, Abhimanyu"],"dc:date.accessioned":["2022-06-15T13:04:38Z"],"dc:date.available":["2022-06-15T13:04:38Z"],"dc:date.issued":["2022-02"],"dc:description.abstract":["In this thesis, we study sequential multi-armed bandit and reinforcement learning in the federated setting, where a group of agents collaborates to improve their collective reward by communicating over a network. We first study the multi-armed bandit problem in a decentralized environment. We study federated bandit learning under several real-world environmental constraints, such as differentially private communication, heavy-tailed perturbations, and the presence of adversarial corruptions. For each of these constraints, we present algorithms with near-optimal regret guarantees and maintain competitive experimental performance on real-world networks. We characterize the asymptotic and minimax rates for these problems via network-dependent lower bounds as well. These algorithms provide substantial improvements over existing work in a variety of real-world and synthetic network topologies. Next, we study the contextual bandit problem in a federated learning setting with differential privacy. In this setting, we propose algorithms that match the optimal rate (up to poly-logarithmic terms) with only a logarithmic communication budget. We extend our approach to heterogeneous federated learning via a kernel-based approach, and also provide a no-regret algorithm for private Gaussian process bandit optimization. Finally, we study reinforcement learning in both the multi-agent and federated setting with linear function approximation. We propose variants of least-squares value iteration algorithms that are provably no-regret with only a constant communication budget. We believe that the future of machine learning entails large-scale cooperation between various data-driven entities, and this work will be beneficial to the development of reliable, scalable, and secure decision-making systems."],"dc:description.degree":["Ph.D."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/143222"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Private and Provably Efficient Federated Decision-Making"],"dc:type":["Thesis"],"thesis:degree_name":["Doctoral","Doctor of Philosophy"]},"updated_at":"2026-07-22T22:21:53Z"}