{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/125683"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/125683","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Towards externally valid machine learning: A spurious correlations perspective","abstract":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-08-01","abstract_html":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-08-01","abstract_has_math":false,"creators":["Salaudeen, Olawale Elijah"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Koyejo, Oluwasanmi","Forsyth, David","Zhao, Han","D'Amour, Alexander"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-07-02","date_published":"2024-07-02","updated_at":"2026-07-22T22:25:02Z","subjects":["Domain Generalization","External Validity","Spurious Correlations","Machine Learning Benchmarks"],"languages":["en","eng"],"rights":["Copyright 2024 Olawale Salaudeen"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/125683","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Koyejo, Oluwasanmi","Forsyth, David","Zhao, Han","D'Amour, Alexander"]},{"key":"dc:creator","label":"Author","values":["Salaudeen, Olawale Elijah"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-07-02","2024-08"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Domain Generalization","External Validity","Spurious Correlations","Machine Learning Benchmarks"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2024 Olawale Salaudeen"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/125683"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-08-01","The student, Olawale Salaudeen, accepted the attached license on 2024-06-29 at 15:42.","The student, Olawale Salaudeen, submitted this Dissertation for approval on 2024-06-29 at 15:51.","This Dissertation was approved for publication on 2024-07-02 at 11:19.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20902 on 2025-02-04 at 21:16:13","As machine learning models permeate critical real-world systems, their reliability becomes paramount. However, their performance often critically depends on how representative their training data is of the deployment domain. This can lead to significant challenges when faced with distribution shifts—situations where the real-world data diverges from the training data. A significant issue under distribution shifts is the presence of spurious correlations—statistical associations in the training data that do not hold in all real-world domains. This dissertation develops methodologies that leverage causality to create machine learning models without spurious correlations, yielding more robust, fair, and ethical decision-making. Causality is crucial because it helps disentangle true causal relationships from mere statistical associations, ensuring that models learn robust, externally valid reasoning. This dissertation also establishes construct validity conditions for evaluating machine learning models under distribution shifts, enabling reliable generalization of robustness from distribution shift benchmarks to the real world. Domain-general models and robust evaluation methods enable the development of externally valid machine learning systems."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Towards externally valid machine learning: A spurious correlations perspective"]}]}],"canonical_facts":{"dc:contributor":["Koyejo, Oluwasanmi","Forsyth, David","Zhao, Han","D'Amour, Alexander"],"dc:creator":["Salaudeen, Olawale Elijah"],"dc:date":["2024-07-02","2024-08"],"dc:description":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-08-01","The student, Olawale Salaudeen, accepted the attached license on 2024-06-29 at 15:42.","The student, Olawale Salaudeen, submitted this Dissertation for approval on 2024-06-29 at 15:51.","This Dissertation was approved for publication on 2024-07-02 at 11:19.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20902 on 2025-02-04 at 21:16:13","As machine learning models permeate critical real-world systems, their reliability becomes paramount. However, their performance often critically depends on how representative their training data is of the deployment domain. This can lead to significant challenges when faced with distribution shifts—situations where the real-world data diverges from the training data. A significant issue under distribution shifts is the presence of spurious correlations—statistical associations in the training data that do not hold in all real-world domains. This dissertation develops methodologies that leverage causality to create machine learning models without spurious correlations, yielding more robust, fair, and ethical decision-making. Causality is crucial because it helps disentangle true causal relationships from mere statistical associations, ensuring that models learn robust, externally valid reasoning. This dissertation also establishes construct validity conditions for evaluating machine learning models under distribution shifts, enabling reliable generalization of robustness from distribution shift benchmarks to the real world. Domain-general models and robust evaluation methods enable the development of externally valid machine learning systems."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/125683"],"dc:language":["en","eng"],"dc:rights":["Copyright 2024 Olawale Salaudeen"],"dc:subject":["Domain Generalization","External Validity","Spurious Correlations","Machine Learning Benchmarks"],"dc:title":["Towards externally valid machine learning: A spurious correlations perspective"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:02Z"}