{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/132528"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/132528","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Provably reliable machine learning systems","abstract":"Machine learning systems, which primarily use deep neural networks (DNNs), serve as critical components in safety-critical applications and compound AI systems. Despite their ubiquity, automated formal reasoning about their reliability has lagged significantly. Neural network verification is NP-hard, requiring expensive end-to-end recomputation whenever networks are modified during iterative deployment cycles. Simultaneously, Large Language Models (LLMs) in compound systems frequently generate outputs that violate syntactic and semantic specifications, leading to cascading failures in automated workflows. Thus, developing reliability techniques for machine learning systems that are simultaneously general, precise, and scalable remains a challenging task. To address these challenges, this dissertation develops a comprehensive framework for provably reliable machine learning systems by establishing incremental verification techniques for DNNs and constrained decoding methods specific to LLMs.","abstract_html":"Machine learning systems, which primarily use deep neural networks (DNNs), serve as critical components in safety-critical applications and compound AI systems. Despite their ubiquity, automated formal reasoning about their reliability has lagged significantly. Neural network verification is NP-hard, requiring expensive end-to-end recomputation whenever networks are modified during iterative deployment cycles. Simultaneously, Large Language Models (LLMs) in compound systems frequently generate outputs that violate syntactic and semantic specifications, leading to cascading failures in automated workflows. Thus, developing reliability techniques for machine learning systems that are simultaneously general, precise, and scalable remains a challenging task. To address these challenges, this dissertation develops a comprehensive framework for provably reliable machine learning systems by establishing incremental verification techniques for DNNs and constrained decoding methods specific to LLMs.","abstract_has_math":false,"creators":["Ugare, Shubham"],"institution":"University of Illinois Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Singh, Gagandeep","Misailovic, Sasa","Zhang, Lingming","Chaudhuri, Swarat"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-12","date_published":"2025-12","updated_at":"2026-07-22T22:25:07Z","subjects":["Machine Learning, Formal Methods"],"languages":["en"],"rights":["Copyright 2025 Shubham Ugare"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/132528","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Singh, Gagandeep","Misailovic, Sasa","Zhang, Lingming","Chaudhuri, Swarat"]},{"key":"dc:creator","label":"Author","values":["Ugare, Shubham"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-12","2025-11-30"]},{"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 Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Machine Learning, Formal Methods"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Shubham Ugare"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/132528"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Machine learning systems, which primarily use deep neural networks (DNNs), serve as critical components in safety-critical applications and compound AI systems. Despite their ubiquity, automated formal reasoning about their reliability has lagged significantly. Neural network verification is NP-hard, requiring expensive end-to-end recomputation whenever networks are modified during iterative deployment cycles. Simultaneously, Large Language Models (LLMs) in compound systems frequently generate outputs that violate syntactic and semantic specifications, leading to cascading failures in automated workflows. Thus, developing reliability techniques for machine learning systems that are simultaneously general, precise, and scalable remains a challenging task. To address these challenges, this dissertation develops a comprehensive framework for provably reliable machine learning systems by establishing incremental verification techniques for DNNs and constrained decoding methods specific to LLMs.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2026-02-19 without embargo terms","The student, Shubham Ugare, accepted the attached license on 2025-11-24 at 19:08.","The student, Shubham Ugare, submitted this Dissertation for approval on 2025-11-24 at 19:14.","This Dissertation was approved for publication on 2025-11-30 at 11:46.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22942 on 2026-02-19 at 18:25:17"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Provably reliable machine learning systems"]}]}],"canonical_facts":{"dc:contributor":["Singh, Gagandeep","Misailovic, Sasa","Zhang, Lingming","Chaudhuri, Swarat"],"dc:creator":["Ugare, Shubham"],"dc:date":["2025-12","2025-11-30"],"dc:description":["Machine learning systems, which primarily use deep neural networks (DNNs), serve as critical components in safety-critical applications and compound AI systems. Despite their ubiquity, automated formal reasoning about their reliability has lagged significantly. Neural network verification is NP-hard, requiring expensive end-to-end recomputation whenever networks are modified during iterative deployment cycles. Simultaneously, Large Language Models (LLMs) in compound systems frequently generate outputs that violate syntactic and semantic specifications, leading to cascading failures in automated workflows. Thus, developing reliability techniques for machine learning systems that are simultaneously general, precise, and scalable remains a challenging task. To address these challenges, this dissertation develops a comprehensive framework for provably reliable machine learning systems by establishing incremental verification techniques for DNNs and constrained decoding methods specific to LLMs.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2026-02-19 without embargo terms","The student, Shubham Ugare, accepted the attached license on 2025-11-24 at 19:08.","The student, Shubham Ugare, submitted this Dissertation for approval on 2025-11-24 at 19:14.","This Dissertation was approved for publication on 2025-11-30 at 11:46.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22942 on 2026-02-19 at 18:25:17"],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/132528"],"dc:language":["en"],"dc:rights":["Copyright 2025 Shubham Ugare"],"dc:subject":["Machine Learning, Formal Methods"],"dc:title":["Provably reliable machine learning systems"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:07Z"}