{"id":{"repo_id":"york","oai_identifier":"oai:yorkspace.library.yorku.ca:10315/43007"},"canonical_url":"https://search.dev.ndltd.org/etd/york/oai:yorkspace.library.yorku.ca:10315/43007","repository":{"repo_id":"york","name":"York University","base_url":"https://yorkspace.library.yorku.ca/oai/request"},"display":{"title":"Refining the sample complexity of comparative learning","abstract":"The PAC (Probably Approximately Correct) framework is a well-established theoretical framework for analyzing the statistical (and sometimes computational) complexity of machine learning tasks. Comparative learning is a recently introduced variation of the PAC framework that interpolates between the two standard extreme settings of realizable and agnostic PAC learning. In comparative learning the labeling is assumed to be from one hypothesis class (the source) while the learner's performance is to be measured against another hypothesis class (the benchmark). This setup allows for incorporating more specific prior knowledge into PAC-type learning bounds, which are known to be otherwise overly pessimistic. In this work we study the sample complexity of a variation of this setting we call proper comparative learning where we require the learning algorithm to output a hypothesis from the benchmark class. This setting represents model distillation tasks, where a predictor with specific requirements (e.g., interpretability) is trained on the labels from another model.","abstract_html":"The PAC (Probably Approximately Correct) framework is a well-established theoretical framework for analyzing the statistical (and sometimes computational) complexity of machine learning tasks. Comparative learning is a recently introduced variation of the PAC framework that interpolates between the two standard extreme settings of realizable and agnostic PAC learning. In comparative learning the labeling is assumed to be from one hypothesis class (the source) while the learner's performance is to be measured against another hypothesis class (the benchmark). This setup allows for incorporating more specific prior knowledge into PAC-type learning bounds, which are known to be otherwise overly pessimistic. In this work we study the sample complexity of a variation of this setting we call proper comparative learning where we require the learning algorithm to output a hypothesis from the benchmark class. This setting represents model distillation tasks, where a predictor with specific requirements (e.g., interpretability) is trained on the labels from another model.","abstract_has_math":false,"creators":["Rahmanian Ashkezari, Sajad"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Urner, Ruth"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-07-23","date_published":"2025-07-23","updated_at":"2026-07-24T06:33:45Z","subjects":["Computer science"],"languages":["en"],"rights":["Author owns copyright, except where explicitly noted. Please contact the author directly with licensing requests."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10315/43007","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Urner, Ruth"]},{"key":"dc:creator","label":"Author","values":["Rahmanian Ashkezari, Sajad"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-07-23T15:16:01Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-07-23T15:16:01Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-07-23"]},{"key":"dc:type","label":"Dc Type","values":["Electronic Thesis or Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Author owns copyright, except where explicitly noted. Please contact the author directly with licensing requests."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10315/43007"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The PAC (Probably Approximately Correct) framework is a well-established theoretical framework for analyzing the statistical (and sometimes computational) complexity of machine learning tasks. Comparative learning is a recently introduced variation of the PAC framework that interpolates between the two standard extreme settings of realizable and agnostic PAC learning. In comparative learning the labeling is assumed to be from one hypothesis class (the source) while the learner's performance is to be measured against another hypothesis class (the benchmark). This setup allows for incorporating more specific prior knowledge into PAC-type learning bounds, which are known to be otherwise overly pessimistic. In this work we study the sample complexity of a variation of this setting we call proper comparative learning where we require the learning algorithm to output a hypothesis from the benchmark class. This setting represents model distillation tasks, where a predictor with specific requirements (e.g., interpretability) is trained on the labels from another model."]},{"key":"dc:title","label":"Title","values":["Refining the sample complexity of comparative learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Urner, Ruth"],"dc:creator":["Rahmanian Ashkezari, Sajad"],"dc:date.accessioned":["2025-07-23T15:16:01Z"],"dc:date.available":["2025-07-23T15:16:01Z"],"dc:date.issued":["2025-07-23"],"dc:description.abstract":["The PAC (Probably Approximately Correct) framework is a well-established theoretical framework for analyzing the statistical (and sometimes computational) complexity of machine learning tasks. Comparative learning is a recently introduced variation of the PAC framework that interpolates between the two standard extreme settings of realizable and agnostic PAC learning. In comparative learning the labeling is assumed to be from one hypothesis class (the source) while the learner's performance is to be measured against another hypothesis class (the benchmark). This setup allows for incorporating more specific prior knowledge into PAC-type learning bounds, which are known to be otherwise overly pessimistic. In this work we study the sample complexity of a variation of this setting we call proper comparative learning where we require the learning algorithm to output a hypothesis from the benchmark class. This setting represents model distillation tasks, where a predictor with specific requirements (e.g., interpretability) is trained on the labels from another model."],"dc:identifier.uri":["https://hdl.handle.net/10315/43007"],"dc:language":["en"],"dc:rights":["Author owns copyright, except where explicitly noted. Please contact the author directly with licensing requests."],"dc:subject":["Computer science"],"dc:title":["Refining the sample complexity of comparative learning"],"dc:type":["Electronic Thesis or Dissertation"]},"updated_at":"2026-07-24T06:33:45Z"}