{"id":{"repo_id":"penn","oai_identifier":"oai:repository.upenn.edu:20.500.14332/32199"},"canonical_url":"https://search.dev.ndltd.org/etd/penn/oai:repository.upenn.edu:20.500.14332/32199","repository":{"repo_id":"penn","name":"University of Pennsylvania","base_url":"https://repository.upenn.edu/server/oai/request"},"display":{"title":"Topics In Differentially Private Statistical Inference","abstract":"This dissertation studies the trade-off between differential privacy and statistical accuracy in parameter estimation problems. We understand the privacy-accuracy trade-off by finding the best achievable accuracy of any differentially private algorithm, also known as the \"privacy-constrained minimax risk\", in a series of statistical problems: Gaussian mean estimation and linear regression, estimation in general parametric models, and non-parametric function estimation. The increasing difficulty and generality of this series is matched by the development of differentially private algorithms such as noisy iterative hard thresholding, and of minimax lower bound techniques such as the score attack.","abstract_html":"This dissertation studies the trade-off between differential privacy and statistical accuracy in parameter estimation problems. We understand the privacy-accuracy trade-off by finding the best achievable accuracy of any differentially private algorithm, also known as the "privacy-constrained minimax risk", in a series of statistical problems: Gaussian mean estimation and linear regression, estimation in general parametric models, and non-parametric function estimation. The increasing difficulty and generality of this series is matched by the development of differentially private algorithms such as noisy iterative hard thresholding, and of minimax lower bound techniques such as the score attack.","abstract_has_math":false,"creators":["Wang, Yichen"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["T. Tony Cai"],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022","date_published":"2022","updated_at":"2026-07-24T03:47:17Z","subjects":[],"languages":["en"],"rights":["Yichen Wang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://repository.upenn.edu/handle/20.500.14332/32199","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["T. Tony Cai"]},{"key":"dc:creator","label":"Author","values":["Wang, Yichen"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2023-05-18T03:46:26.000"]},{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-05-22T18:39:34Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-07-05T00:00:00Z"]},{"key":"dc:date.issued","label":"Date","values":["2022"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation/Thesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Yichen Wang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://repository.upenn.edu/handle/20.500.14332/32199"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This dissertation studies the trade-off between differential privacy and statistical accuracy in parameter estimation problems. We understand the privacy-accuracy trade-off by finding the best achievable accuracy of any differentially private algorithm, also known as the \"privacy-constrained minimax risk\", in a series of statistical problems: Gaussian mean estimation and linear regression, estimation in general parametric models, and non-parametric function estimation. The increasing difficulty and generality of this series is matched by the development of differentially private algorithms such as noisy iterative hard thresholding, and of minimax lower bound techniques such as the score attack."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Doctor of Philosophy (PhD)"]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Topics In Differentially Private Statistical Inference"]}]}],"canonical_facts":{"dc:contributor.advisor":["T. Tony Cai"],"dc:creator":["Wang, Yichen"],"dc:date":["2023-05-18T03:46:26.000"],"dc:date.accessioned":["2023-05-22T18:39:34Z"],"dc:date.available":["2025-07-05T00:00:00Z"],"dc:date.issued":["2022"],"dc:description.abstract":["This dissertation studies the trade-off between differential privacy and statistical accuracy in parameter estimation problems. We understand the privacy-accuracy trade-off by finding the best achievable accuracy of any differentially private algorithm, also known as the \"privacy-constrained minimax risk\", in a series of statistical problems: Gaussian mean estimation and linear regression, estimation in general parametric models, and non-parametric function estimation. The increasing difficulty and generality of this series is matched by the development of differentially private algorithms such as noisy iterative hard thresholding, and of minimax lower bound techniques such as the score attack."],"dc:description.degree":["Doctor of Philosophy (PhD)"],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://repository.upenn.edu/handle/20.500.14332/32199"],"dc:language":["en"],"dc:rights":["Yichen Wang"],"dc:title":["Topics In Differentially Private Statistical Inference"],"dc:type":["Dissertation/Thesis"]},"updated_at":"2026-07-24T03:47:17Z"}