{"id":{"repo_id":"bu","oai_identifier":"oai:open.bu.edu:2144/53440"},"canonical_url":"https://search.ndltd.org/etd/bu/oai:open.bu.edu:2144/53440","repository":{"repo_id":"bu","name":"Boston University","base_url":"https://open.bu.edu/oai/request"},"display":{"title":"Improving performance, efficiency, and stability in self-supervised machine learning","abstract":"This dissertation advances self-supervised learning procedures as a principled response to the labeled data bottleneck, a fundamental and pervasive constraint in applied machine learning. In many real-world settings, acquiring sufficient labeled examples is prohibitively expensive or logistically infeasible, yet standard supervised approaches offer little recourse. By leveraging multi-agent reinforcement learning and adversarial training, models can learn from richer, less curated signals, reducing dependence on hand-labeled data while preserving task-relevant inductive biases. First, we introduce a biologically plausible complex-valued neural network architecture inspired by neural synchrony in the brain. A novel activation function enables neurons to respond preferentially to temporally synchronized inputs, yielding improved performance on benchmark datasets compared to real-valued fully connected networks. We demonstrate how complex-valued neural architecture can improve the performance of adversarial learning algorithms without breaking the delicate balance between adversarial networks. Second, we develop a learning framework for computing coarse correlated equilibria (CCE) in large, simultaneous-move games. The method combines no-regret learning, self-play, and deep neural networks to approximate CCE values and iteratively guide a tree search process. The resulting algorithm generalizes well across game states and outperforms existing multi-agent reinforcement learning baselines. Third, we propose a modified Wasserstein GAN (WGAN) for reweighting biased survey data to match a reference population. Instead of generating synthetic data, the generator learns sample weights that minimize distributional discrepancy between the biased and reference datasets. Applied to real-world surveys, the model recovers richer variable interactions and achieves superior predictive performance on outcomes such as COVID-19 vaccination and insurance rates. Building on the survey reweighting framework, we further improve performance by incorporating complex-valued network components and applying the no-regret stopping criterion from the second project, with both advances yielding measurably better reweighting. Motivated by the success of no-regret stopping in adversarial training, we then apply this criterion to an entirely different domain: unsupervised domain adaptation via Domain Adversarial Neural Networks (DANN). Despite the architectural differences between WGANs and DANN, the no-regret stopping criterion transfers naturally. Both WGANs and DANN share the fundamental structure of a minimax adversarial game, making the transfer principled. Applied to DANN, the no-regret stopping criterion alone produces statistically significant improvements in target domain generalization across multiple benchmarks, confirmed by statistical tests of significance. Together, these contributions demonstrate that aligning neural learning systems with the underlying structure of their domain leads to more robust, efficient, and accurate models. This thesis advocates for a domain-informed approach to neural network design, enabling better solutions to complex applied problems across biology, game theory, and statistical inference.","abstract_html":"This dissertation advances self-supervised learning procedures as a principled response to the labeled data bottleneck, a fundamental and pervasive constraint in applied machine learning. In many real-world settings, acquiring sufficient labeled examples is prohibitively expensive or logistically infeasible, yet standard supervised approaches offer little recourse. By leveraging multi-agent reinforcement learning and adversarial training, models can learn from richer, less curated signals, reducing dependence on hand-labeled data while preserving task-relevant inductive biases. First, we introduce a biologically plausible complex-valued neural network architecture inspired by neural synchrony in the brain. A novel activation function enables neurons to respond preferentially to temporally synchronized inputs, yielding improved performance on benchmark datasets compared to real-valued fully connected networks. We demonstrate how complex-valued neural architecture can improve the performance of adversarial learning algorithms without breaking the delicate balance between adversarial networks. Second, we develop a learning framework for computing coarse correlated equilibria (CCE) in large, simultaneous-move games. The method combines no-regret learning, self-play, and deep neural networks to approximate CCE values and iteratively guide a tree search process. The resulting algorithm generalizes well across game states and outperforms existing multi-agent reinforcement learning baselines. Third, we propose a modified Wasserstein GAN (WGAN) for reweighting biased survey data to match a reference population. Instead of generating synthetic data, the generator learns sample weights that minimize distributional discrepancy between the biased and reference datasets. Applied to real-world surveys, the model recovers richer variable interactions and achieves superior predictive performance on outcomes such as COVID-19 vaccination and insurance rates. Building on the survey reweighting framework, we further improve performance by incorporating complex-valued network components and applying the no-regret stopping criterion from the second project, with both advances yielding measurably better reweighting. Motivated by the success of no-regret stopping in adversarial training, we then apply this criterion to an entirely different domain: unsupervised domain adaptation via Domain Adversarial Neural Networks (DANN). Despite the architectural differences between WGANs and DANN, the no-regret stopping criterion transfers naturally. Both WGANs and DANN share the fundamental structure of a minimax adversarial game, making the transfer principled. Applied to DANN, the no-regret stopping criterion alone produces statistically significant improvements in target domain generalization across multiple benchmarks, confirmed by statistical tests of significance. Together, these contributions demonstrate that aligning neural learning systems with the underlying structure of their domain leads to more robust, efficient, and accurate models. This thesis advocates for a domain-informed approach to neural network design, enabling better solutions to complex applied problems across biology, game theory, and statistical inference.","abstract_has_math":false,"creators":["Yu, Ryan"],"institution":"Boston University","degree_name":"Doctor of Philosophy","degree_level":"doctoral","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Olshevsky, Alexander"],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-18T20:19:39Z","subjects":["Computer science","Adversarial Networks","Neural Networks","Reinforcement Learning"],"languages":["en_US"],"rights":["Attribution 4.0 International"],"rights_urls":["http://creativecommons.org/licenses/by/4.0/"],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2144/53440","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/2144/53440","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.bu.edu/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Aopen.bu.edu%3A2144%2F53440","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Olshevsky, Alexander"]},{"key":"dc:creator","label":"Author","values":["Yu, Ryan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-09-10T19:26:34Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-09-10T19:26:34Z"]},{"key":"dc:date.issued","label":"Date","values":["2026"]},{"key":"dc:date.updated","label":"Dc Date Updated","values":["2026-09-09T22:15:42Z"]},{"key":"dc:type","label":"Dc Type","values":["Thesis/Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"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":["Boston University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer science","Adversarial Networks","Neural Networks","Reinforcement Learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://creativecommons.org/licenses/by/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/2144/53440"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["2026"]},{"key":"dc:description.abstract","label":"Abstract","values":["This dissertation advances self-supervised learning procedures as a principled response to the labeled data bottleneck, a fundamental and pervasive constraint in applied machine learning. In many real-world settings, acquiring sufficient labeled examples is prohibitively expensive or logistically infeasible, yet standard supervised approaches offer little recourse. By leveraging multi-agent reinforcement learning and adversarial training, models can learn from richer, less curated signals, reducing dependence on hand-labeled data while preserving task-relevant inductive biases. First, we introduce a biologically plausible complex-valued neural network architecture inspired by neural synchrony in the brain. A novel activation function enables neurons to respond preferentially to temporally synchronized inputs, yielding improved performance on benchmark datasets compared to real-valued fully connected networks. We demonstrate how complex-valued neural architecture can improve the performance of adversarial learning algorithms without breaking the delicate balance between adversarial networks. Second, we develop a learning framework for computing coarse correlated equilibria (CCE) in large, simultaneous-move games. The method combines no-regret learning, self-play, and deep neural networks to approximate CCE values and iteratively guide a tree search process. The resulting algorithm generalizes well across game states and outperforms existing multi-agent reinforcement learning baselines. Third, we propose a modified Wasserstein GAN (WGAN) for reweighting biased survey data to match a reference population. Instead of generating synthetic data, the generator learns sample weights that minimize distributional discrepancy between the biased and reference datasets. Applied to real-world surveys, the model recovers richer variable interactions and achieves superior predictive performance on outcomes such as COVID-19 vaccination and insurance rates. Building on the survey reweighting framework, we further improve performance by incorporating complex-valued network components and applying the no-regret stopping criterion from the second project, with both advances yielding measurably better reweighting. Motivated by the success of no-regret stopping in adversarial training, we then apply this criterion to an entirely different domain: unsupervised domain adaptation via Domain Adversarial Neural Networks (DANN). Despite the architectural differences between WGANs and DANN, the no-regret stopping criterion transfers naturally. Both WGANs and DANN share the fundamental structure of a minimax adversarial game, making the transfer principled. Applied to DANN, the no-regret stopping criterion alone produces statistically significant improvements in target domain generalization across multiple benchmarks, confirmed by statistical tests of significance. Together, these contributions demonstrate that aligning neural learning systems with the underlying structure of their domain leads to more robust, efficient, and accurate models. This thesis advocates for a domain-informed approach to neural network design, enabling better solutions to complex applied problems across biology, game theory, and statistical inference."]},{"key":"dc:title","label":"Title","values":["Improving performance, efficiency, and stability in self-supervised machine learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Olshevsky, Alexander"],"dc:creator":["Yu, Ryan"],"dc:date.accessioned":["2026-09-10T19:26:34Z"],"dc:date.available":["2026-09-10T19:26:34Z"],"dc:date.issued":["2026"],"dc:date.updated":["2026-09-09T22:15:42Z"],"dc:description":["2026"],"dc:description.abstract":["This dissertation advances self-supervised learning procedures as a principled response to the labeled data bottleneck, a fundamental and pervasive constraint in applied machine learning. In many real-world settings, acquiring sufficient labeled examples is prohibitively expensive or logistically infeasible, yet standard supervised approaches offer little recourse. By leveraging multi-agent reinforcement learning and adversarial training, models can learn from richer, less curated signals, reducing dependence on hand-labeled data while preserving task-relevant inductive biases. First, we introduce a biologically plausible complex-valued neural network architecture inspired by neural synchrony in the brain. A novel activation function enables neurons to respond preferentially to temporally synchronized inputs, yielding improved performance on benchmark datasets compared to real-valued fully connected networks. We demonstrate how complex-valued neural architecture can improve the performance of adversarial learning algorithms without breaking the delicate balance between adversarial networks. Second, we develop a learning framework for computing coarse correlated equilibria (CCE) in large, simultaneous-move games. The method combines no-regret learning, self-play, and deep neural networks to approximate CCE values and iteratively guide a tree search process. The resulting algorithm generalizes well across game states and outperforms existing multi-agent reinforcement learning baselines. Third, we propose a modified Wasserstein GAN (WGAN) for reweighting biased survey data to match a reference population. Instead of generating synthetic data, the generator learns sample weights that minimize distributional discrepancy between the biased and reference datasets. Applied to real-world surveys, the model recovers richer variable interactions and achieves superior predictive performance on outcomes such as COVID-19 vaccination and insurance rates. Building on the survey reweighting framework, we further improve performance by incorporating complex-valued network components and applying the no-regret stopping criterion from the second project, with both advances yielding measurably better reweighting. Motivated by the success of no-regret stopping in adversarial training, we then apply this criterion to an entirely different domain: unsupervised domain adaptation via Domain Adversarial Neural Networks (DANN). Despite the architectural differences between WGANs and DANN, the no-regret stopping criterion transfers naturally. Both WGANs and DANN share the fundamental structure of a minimax adversarial game, making the transfer principled. Applied to DANN, the no-regret stopping criterion alone produces statistically significant improvements in target domain generalization across multiple benchmarks, confirmed by statistical tests of significance. Together, these contributions demonstrate that aligning neural learning systems with the underlying structure of their domain leads to more robust, efficient, and accurate models. This thesis advocates for a domain-informed approach to neural network design, enabling better solutions to complex applied problems across biology, game theory, and statistical inference."],"dc:identifier.uri":["https://hdl.handle.net/2144/53440"],"dc:language.iso":["en_US"],"dc:rights":["Attribution 4.0 International"],"dc:rights.uri":["http://creativecommons.org/licenses/by/4.0/"],"dc:subject":["Computer science","Adversarial Networks","Neural Networks","Reinforcement Learning"],"dc:title":["Improving performance, efficiency, and stability in self-supervised machine learning"],"dc:type":["Thesis/Dissertation"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["doctoral"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["Boston University"]},"updated_at":"2026-11-18T20:19:39Z"}