{"id":{"repo_id":"penn","oai_identifier":"oai:repository.upenn.edu:20.500.14332/61722"},"canonical_url":"https://search.dev.ndltd.org/etd/penn/oai:repository.upenn.edu:20.500.14332/61722","repository":{"repo_id":"penn","name":"University of Pennsylvania","base_url":"https://repository.upenn.edu/server/oai/request"},"display":{"title":"REFRAMING ALGORITHMIC FAIRNESS: A PARADIGM FOR FAIR, ACCURATE, AND FLEXIBLE MODEL DEVELOPMENT","abstract":"Machine learning increasingly shapes high-stakes decisions, offering benefits like improved efficiency and accuracy—but also raising challenges when systems fail. Unlike human decision-makers, algorithms often lack clear paths for recourse or repair. This dissertation develops algorithmic tools for responsible and flexible machine learning, focusing on models that can adapt post-deployment, incorporate human feedback, and scale to real-world use. It introduces bias bounties--- a framework for users to collaboratively identify and patch model failures—and offers algorithms for post-processing models to meet fairness goals without retraining or rigid assumptions. It advances the theory of multicalibration, showing when fairness can be achieved without sacrificing accuracy, and proposes a simple swap-regret formulation of multicalibration which can be used in a variety of contexts, such as collaborative learning. Finally, it leverages multicalibration for flexible model development, demonstrating techniques to flexibly postprocess multicalibrated predictors to meet various downstream fairness objectives.","abstract_html":"Machine learning increasingly shapes high-stakes decisions, offering benefits like improved efficiency and accuracy—but also raising challenges when systems fail. Unlike human decision-makers, algorithms often lack clear paths for recourse or repair. This dissertation develops algorithmic tools for responsible and flexible machine learning, focusing on models that can adapt post-deployment, incorporate human feedback, and scale to real-world use. It introduces bias bounties--- a framework for users to collaboratively identify and patch model failures—and offers algorithms for post-processing models to meet fairness goals without retraining or rigid assumptions. It advances the theory of multicalibration, showing when fairness can be achieved without sacrificing accuracy, and proposes a simple swap-regret formulation of multicalibration which can be used in a variety of contexts, such as collaborative learning. Finally, it leverages multicalibration for flexible model development, demonstrating techniques to flexibly postprocess multicalibrated predictors to meet various downstream fairness objectives.","abstract_has_math":false,"creators":["Globus-Harris, Ira"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Kearns, Michael","Roth, Aaron"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-07-24T03:46:55Z","subjects":["Computer Sciences"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://repository.upenn.edu/handle/20.500.14332/61722","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Kearns, Michael","Roth, Aaron"]},{"key":"dc:creator","label":"Author","values":["Globus-Harris, Ira"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-09-02T16:27:10Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-09-02T16:27:10Z"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation/Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer Sciences"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://repository.upenn.edu/handle/20.500.14332/61722"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Machine learning increasingly shapes high-stakes decisions, offering benefits like improved efficiency and accuracy—but also raising challenges when systems fail. Unlike human decision-makers, algorithms often lack clear paths for recourse or repair. This dissertation develops algorithmic tools for responsible and flexible machine learning, focusing on models that can adapt post-deployment, incorporate human feedback, and scale to real-world use. It introduces bias bounties--- a framework for users to collaboratively identify and patch model failures—and offers algorithms for post-processing models to meet fairness goals without retraining or rigid assumptions. It advances the theory of multicalibration, showing when fairness can be achieved without sacrificing accuracy, and proposes a simple swap-regret formulation of multicalibration which can be used in a variety of contexts, such as collaborative learning. Finally, it leverages multicalibration for flexible model development, demonstrating techniques to flexibly postprocess multicalibrated predictors to meet various downstream fairness objectives."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Doctor of Philosophy (PhD)"]},{"key":"dc:title","label":"Title","values":["REFRAMING ALGORITHMIC FAIRNESS: A PARADIGM FOR FAIR, ACCURATE, AND FLEXIBLE MODEL DEVELOPMENT"]}]}],"canonical_facts":{"dc:contributor.advisor":["Kearns, Michael","Roth, Aaron"],"dc:creator":["Globus-Harris, Ira"],"dc:date.accessioned":["2025-09-02T16:27:10Z"],"dc:date.available":["2025-09-02T16:27:10Z"],"dc:date.issued":["2025"],"dc:description.abstract":["Machine learning increasingly shapes high-stakes decisions, offering benefits like improved efficiency and accuracy—but also raising challenges when systems fail. Unlike human decision-makers, algorithms often lack clear paths for recourse or repair. This dissertation develops algorithmic tools for responsible and flexible machine learning, focusing on models that can adapt post-deployment, incorporate human feedback, and scale to real-world use. It introduces bias bounties--- a framework for users to collaboratively identify and patch model failures—and offers algorithms for post-processing models to meet fairness goals without retraining or rigid assumptions. It advances the theory of multicalibration, showing when fairness can be achieved without sacrificing accuracy, and proposes a simple swap-regret formulation of multicalibration which can be used in a variety of contexts, such as collaborative learning. Finally, it leverages multicalibration for flexible model development, demonstrating techniques to flexibly postprocess multicalibrated predictors to meet various downstream fairness objectives."],"dc:description.degree":["Doctor of Philosophy (PhD)"],"dc:identifier.uri":["https://repository.upenn.edu/handle/20.500.14332/61722"],"dc:language.iso":["en"],"dc:subject":["Computer Sciences"],"dc:title":["REFRAMING ALGORITHMIC FAIRNESS: A PARADIGM FOR FAIR, ACCURATE, AND FLEXIBLE MODEL DEVELOPMENT"],"dc:type":["Dissertation/Thesis"]},"updated_at":"2026-07-24T03:46:55Z"}