{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/112878"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/112878","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Online Learning for Resource Allocation in Wireless Networks: Fairness, Communication Efficiency, and Data Privacy","abstract":"As the Next-Generation (NextG, 5G and beyond) wireless network supports a wider range of services, optimization of resource allocation plays a crucial role in ensuring efficient use of the (limited) available network resources. Note that resource allocation may require knowledge of network parameters (e.g., channel state information and available power level) for package schedule. However, wireless networks operate in an uncertain environment where, in many practical scenarios, these parameters are unknown before decisions are made. In the absence of network parameters, a network controller, who performs resource allocation, may have to make decisions (aimed at optimizing network performance and satisfying users' QoS requirements) while emph{learning}. To that end, this dissertation studies two novel online learning problems that are motivated by autonomous resource management in NextG. Key contributions of the dissertation are two-fold. First, we study reward maximization under uncertainty with fairness constraints, which is motivated by wireless scheduling with Quality of Service constraints (e.g., minimum delivery ratio requirement) under uncertainty. We formulate a framework of combinatorial bandits with fairness constraints and develop a fair learning algorithm that successfully addresses the tradeoff between reward maximization and fairness constraints. This framework can also be applied to several other real-world applications, such as online advertising and crowdsourcing. Second, we consider global reward maximization under uncertainty with distributed biased feedback, which is motivated by the problem of cellular network configuration for optimizing network-level performance (e.g., average user-perceived Quality of Experience). We study both the linear-parameterized and non-parametric global reward functions, which are modeled as distributed linear bandits and kernelized bandits, respectively. For each model, we propose a learning algorithmic framework that can be integrated with different differential privacy models. We show that the proposed algorithms can achieve a near-optimal regret in a communication-efficient manner while protecting users' data privacy ``for free''. Our findings reveal that our developed algorithms outperform the state-of-the-art solutions in terms of the tradeoff among the regret, communication efficiency, and computation complexity. In addition, our proposed models and online learning algorithms can also be applied to several other real-world applications, e.g., dynamic pricing and public policy making, which may be of independent interest to a broader research community.","abstract_html":"As the Next-Generation (NextG, 5G and beyond) wireless network supports a wider range of services, optimization of resource allocation plays a crucial role in ensuring efficient use of the (limited) available network resources. Note that resource allocation may require knowledge of network parameters (e.g., channel state information and available power level) for package schedule. However, wireless networks operate in an uncertain environment where, in many practical scenarios, these parameters are unknown before decisions are made. In the absence of network parameters, a network controller, who performs resource allocation, may have to make decisions (aimed at optimizing network performance and satisfying users' QoS requirements) while emph{learning}. To that end, this dissertation studies two novel online learning problems that are motivated by autonomous resource management in NextG. Key contributions of the dissertation are two-fold. First, we study reward maximization under uncertainty with fairness constraints, which is motivated by wireless scheduling with Quality of Service constraints (e.g., minimum delivery ratio requirement) under uncertainty. We formulate a framework of combinatorial bandits with fairness constraints and develop a fair learning algorithm that successfully addresses the tradeoff between reward maximization and fairness constraints. This framework can also be applied to several other real-world applications, such as online advertising and crowdsourcing. Second, we consider global reward maximization under uncertainty with distributed biased feedback, which is motivated by the problem of cellular network configuration for optimizing network-level performance (e.g., average user-perceived Quality of Experience). We study both the linear-parameterized and non-parametric global reward functions, which are modeled as distributed linear bandits and kernelized bandits, respectively. For each model, we propose a learning algorithmic framework that can be integrated with different differential privacy models. We show that the proposed algorithms can achieve a near-optimal regret in a communication-efficient manner while protecting users' data privacy ``for free''. Our findings reveal that our developed algorithms outperform the state-of-the-art solutions in terms of the tradeoff among the regret, communication efficiency, and computation complexity. In addition, our proposed models and online learning algorithms can also be applied to several other real-world applications, e.g., dynamic pricing and public policy making, which may be of independent interest to a broader research community.","abstract_has_math":false,"creators":["Li, Fengjiao"],"institution":"Virginia Tech","degree_name":"Doctor of Philosophy","degree_level":"doctoral","degree_discipline":"Computer Science and Applications","degree_department":"Computer Science and Applications","school":null,"contributors":[],"advisors":[],"committee_chairs":["Ji, Bo"],"committee_members":["Lourentzou, Ismini","Wang, Yu","Wu, Jie","Raghvendra, Sharath"],"year":2022,"date_issued":"2022-12-13","date_published":"2022-12-13","updated_at":"2026-07-22T22:19:19Z","subjects":["resource allocation","online bandit learning","fairness","communication efficiency","data privacy"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:36040"],"render_values":[{"text":"vt_gsexam:36040","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/10919/112878","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Ji, Bo"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Lourentzou, Ismini","Wang, Yu","Wu, Jie","Raghvendra, Sharath"]},{"key":"dc:contributor.department","label":"Department","values":["Computer Science and Applications"]},{"key":"dc:creator","label":"Author","values":["Li, Fengjiao"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-12-14T09:00:09Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-12-14T09:00:09Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-12-13"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science and Applications"]},{"key":"thesis:degree_level","label":"Degree Level","values":["doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["resource allocation","online bandit learning","fairness","communication efficiency","data privacy"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:36040"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/10919/112878"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["As the Next-Generation (NextG, 5G and beyond) wireless network supports a wider range of services, optimization of resource allocation plays a crucial role in ensuring efficient use of the (limited) available network resources. Note that resource allocation may require knowledge of network parameters (e.g., channel state information and available power level) for package schedule. However, wireless networks operate in an uncertain environment where, in many practical scenarios, these parameters are unknown before decisions are made. In the absence of network parameters, a network controller, who performs resource allocation, may have to make decisions (aimed at optimizing network performance and satisfying users' QoS requirements) while emph{learning}. To that end, this dissertation studies two novel online learning problems that are motivated by autonomous resource management in NextG. Key contributions of the dissertation are two-fold. First, we study reward maximization under uncertainty with fairness constraints, which is motivated by wireless scheduling with Quality of Service constraints (e.g., minimum delivery ratio requirement) under uncertainty. We formulate a framework of combinatorial bandits with fairness constraints and develop a fair learning algorithm that successfully addresses the tradeoff between reward maximization and fairness constraints. This framework can also be applied to several other real-world applications, such as online advertising and crowdsourcing. Second, we consider global reward maximization under uncertainty with distributed biased feedback, which is motivated by the problem of cellular network configuration for optimizing network-level performance (e.g., average user-perceived Quality of Experience). We study both the linear-parameterized and non-parametric global reward functions, which are modeled as distributed linear bandits and kernelized bandits, respectively. For each model, we propose a learning algorithmic framework that can be integrated with different differential privacy models. We show that the proposed algorithms can achieve a near-optimal regret in a communication-efficient manner while protecting users' data privacy ``for free''. Our findings reveal that our developed algorithms outperform the state-of-the-art solutions in terms of the tradeoff among the regret, communication efficiency, and computation complexity. In addition, our proposed models and online learning algorithms can also be applied to several other real-world applications, e.g., dynamic pricing and public policy making, which may be of independent interest to a broader research community."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["As the Next-Generation (NextG) wireless network supports a wider range of services, optimization of resource allocation plays a crucial role in ensuring efficient use of the (limited) available network resources. Note that resource allocation may require knowledge of network parameters (e.g., channel state information and available power level) for package schedule. However, wireless networks operate in an uncertain environment where, in many practical scenarios, these parameters are unknown before decisions are made. In the absence of network parameters, a network controller, who performs resource allocation, may have to make decisions (aimed at optimizing network performance and satisfying users' QoS requirements) while emph{learning}. To that end, this dissertation studies two novel online learning problems that are motivated by resource allocation in the presence uncertainty in NextG. Key contributions of the dissertation are two-fold. First, we study reward maximization under uncertainty with fairness constraints, which is motivated by wireless scheduling with Quality of Service constraints (e.g., minimum delivery ratio requirement) under uncertainty. We formulate a framework of combinatorial bandits with fairness constraints and develop a fair learning algorithm that successfully addresses the tradeoff between reward maximization and fairness constraints. This framework can also be applied to several other real-world applications, such as online advertising and crowdsourcing. Second, we consider global reward maximization under uncertainty with distributed biased feedback, which is motivated by the problem of cellular network configuration for optimizing network-level performance (e.g., average user-perceived Quality of Experience). We consider both the linear-parameterized and non-parametric (unknown) global reward functions, which are modeled as distributed linear bandits and kernelized bandits, respectively. For each model, we propose a learning algorithmic framework that integrate different privacy models according to different privacy requirements or different scenarios. We show that the proposed algorithms can learn the unknown functions in a communication-efficient manner while protecting users' data privacy ``for free''. Our findings reveal that our developed algorithms outperform the state-of-the-art solutions in terms of the tradeoff among the regret, communication efficiency, and computation complexity. In addition, our proposed models and online learning algorithms can also be applied to several other real-world applications, e.g., dynamic pricing and public policy making, which may be of independent interest to a broader research community."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Doctor of Philosophy"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Online Learning for Resource Allocation in Wireless Networks: Fairness, Communication Efficiency, and Data Privacy"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Ji, Bo"],"dc:contributor.committeemember":["Lourentzou, Ismini","Wang, Yu","Wu, Jie","Raghvendra, Sharath"],"dc:contributor.department":["Computer Science and Applications"],"dc:creator":["Li, Fengjiao"],"dc:date.accessioned":["2022-12-14T09:00:09Z"],"dc:date.available":["2022-12-14T09:00:09Z"],"dc:date.issued":["2022-12-13"],"dc:description.abstract":["As the Next-Generation (NextG, 5G and beyond) wireless network supports a wider range of services, optimization of resource allocation plays a crucial role in ensuring efficient use of the (limited) available network resources. Note that resource allocation may require knowledge of network parameters (e.g., channel state information and available power level) for package schedule. However, wireless networks operate in an uncertain environment where, in many practical scenarios, these parameters are unknown before decisions are made. In the absence of network parameters, a network controller, who performs resource allocation, may have to make decisions (aimed at optimizing network performance and satisfying users' QoS requirements) while emph{learning}. To that end, this dissertation studies two novel online learning problems that are motivated by autonomous resource management in NextG. Key contributions of the dissertation are two-fold. First, we study reward maximization under uncertainty with fairness constraints, which is motivated by wireless scheduling with Quality of Service constraints (e.g., minimum delivery ratio requirement) under uncertainty. We formulate a framework of combinatorial bandits with fairness constraints and develop a fair learning algorithm that successfully addresses the tradeoff between reward maximization and fairness constraints. This framework can also be applied to several other real-world applications, such as online advertising and crowdsourcing. Second, we consider global reward maximization under uncertainty with distributed biased feedback, which is motivated by the problem of cellular network configuration for optimizing network-level performance (e.g., average user-perceived Quality of Experience). We study both the linear-parameterized and non-parametric global reward functions, which are modeled as distributed linear bandits and kernelized bandits, respectively. For each model, we propose a learning algorithmic framework that can be integrated with different differential privacy models. We show that the proposed algorithms can achieve a near-optimal regret in a communication-efficient manner while protecting users' data privacy ``for free''. Our findings reveal that our developed algorithms outperform the state-of-the-art solutions in terms of the tradeoff among the regret, communication efficiency, and computation complexity. In addition, our proposed models and online learning algorithms can also be applied to several other real-world applications, e.g., dynamic pricing and public policy making, which may be of independent interest to a broader research community."],"dc:description.abstractgeneral":["As the Next-Generation (NextG) wireless network supports a wider range of services, optimization of resource allocation plays a crucial role in ensuring efficient use of the (limited) available network resources. Note that resource allocation may require knowledge of network parameters (e.g., channel state information and available power level) for package schedule. However, wireless networks operate in an uncertain environment where, in many practical scenarios, these parameters are unknown before decisions are made. In the absence of network parameters, a network controller, who performs resource allocation, may have to make decisions (aimed at optimizing network performance and satisfying users' QoS requirements) while emph{learning}. To that end, this dissertation studies two novel online learning problems that are motivated by resource allocation in the presence uncertainty in NextG. Key contributions of the dissertation are two-fold. First, we study reward maximization under uncertainty with fairness constraints, which is motivated by wireless scheduling with Quality of Service constraints (e.g., minimum delivery ratio requirement) under uncertainty. We formulate a framework of combinatorial bandits with fairness constraints and develop a fair learning algorithm that successfully addresses the tradeoff between reward maximization and fairness constraints. This framework can also be applied to several other real-world applications, such as online advertising and crowdsourcing. Second, we consider global reward maximization under uncertainty with distributed biased feedback, which is motivated by the problem of cellular network configuration for optimizing network-level performance (e.g., average user-perceived Quality of Experience). We consider both the linear-parameterized and non-parametric (unknown) global reward functions, which are modeled as distributed linear bandits and kernelized bandits, respectively. For each model, we propose a learning algorithmic framework that integrate different privacy models according to different privacy requirements or different scenarios. We show that the proposed algorithms can learn the unknown functions in a communication-efficient manner while protecting users' data privacy ``for free''. Our findings reveal that our developed algorithms outperform the state-of-the-art solutions in terms of the tradeoff among the regret, communication efficiency, and computation complexity. In addition, our proposed models and online learning algorithms can also be applied to several other real-world applications, e.g., dynamic pricing and public policy making, which may be of independent interest to a broader research community."],"dc:description.degree":["Doctor of Philosophy"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:36040"],"dc:identifier.uri":["http://hdl.handle.net/10919/112878"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["resource allocation","online bandit learning","fairness","communication efficiency","data privacy"],"dc:title":["Online Learning for Resource Allocation in Wireless Networks: Fairness, Communication Efficiency, and Data Privacy"],"dc:type":["Dissertation"],"thesis:degree_discipline":["Computer Science and Applications"],"thesis:degree_level":["doctoral"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:19:19Z"}