{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129164"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129164","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Certifying robustness in inference and learning problems","abstract":"There is a rich literature of algorithms for inference, prediction, and decision-making problems when the underlying distributions governing the data are known and well-modeled. The research from the past few decades has provided powerful learning algorithms when such distributions cannot be easily modeled, for instance with high dimensional data. As a result, such data driven methods are becoming ubiquitous in a wide variety of real-life applications, including safety-critical ones such as self-driving and medical diagnosis. In order for the reliable and safe deployment of such algorithms in practice, there exist several imminent questions to be answered. In this dissertation, a few topics in robustness of inference and learning methods are studied. One of the key issues with data-driven methods in practice is unexpected changes that can occur at inference time potentially affecting the performance of these methods, for instance, deviations in the data generating distributions, irrelevant or unrecognizable inputs, and adversarial attacks from unknown sources. The underlying theme connecting the topics studied in this dissertation is the development of learning algorithms robust to such unexpected, potentially harmful, deviations. Broadly, three problems in robust inference and learning are discussed in this dissertation - out-of-distribution detection for machine learning models, detection robust to distribution shifts, and multi-player multi-armed bandits robust to adversarial attacks. Principled approaches for these problems with theoretical guarantees are derived using tools from statistics, information theory and optimization, that are practical, resilient and efficiently implementable.","abstract_html":"There is a rich literature of algorithms for inference, prediction, and decision-making problems when the underlying distributions governing the data are known and well-modeled. The research from the past few decades has provided powerful learning algorithms when such distributions cannot be easily modeled, for instance with high dimensional data. As a result, such data driven methods are becoming ubiquitous in a wide variety of real-life applications, including safety-critical ones such as self-driving and medical diagnosis. In order for the reliable and safe deployment of such algorithms in practice, there exist several imminent questions to be answered. In this dissertation, a few topics in robustness of inference and learning methods are studied. One of the key issues with data-driven methods in practice is unexpected changes that can occur at inference time potentially affecting the performance of these methods, for instance, deviations in the data generating distributions, irrelevant or unrecognizable inputs, and adversarial attacks from unknown sources. The underlying theme connecting the topics studied in this dissertation is the development of learning algorithms robust to such unexpected, potentially harmful, deviations. Broadly, three problems in robust inference and learning are discussed in this dissertation - out-of-distribution detection for machine learning models, detection robust to distribution shifts, and multi-player multi-armed bandits robust to adversarial attacks. Principled approaches for these problems with theoretical guarantees are derived using tools from statistics, information theory and optimization, that are practical, resilient and efficiently implementable.","abstract_has_math":false,"creators":["Magesh, Akshayaa"],"institution":"University of Illinois Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Veeravalli, Venugopal V.","Rayadurgam, Srikant","Raginsky, Maxim","Shomorony, Ilan"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-02-07","date_published":"2025-02-07","updated_at":"2026-07-22T22:25:04Z","subjects":["Out-of-Distribution Detection","Robust Hypothesis Testing","Distributional Robustness","Multi-Player Multi-Armed Bandits","Adversarial Robustness"],"languages":["eng","en"],"rights":["Copyright 2025 Akshayaa Magesh"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129164","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Veeravalli, Venugopal V.","Rayadurgam, Srikant","Raginsky, Maxim","Shomorony, Ilan"]},{"key":"dc:creator","label":"Author","values":["Magesh, Akshayaa"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-02-07","2025-05"]},{"key":"dc:type","label":"Dc Type","values":["Thesis","text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"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":["Out-of-Distribution Detection","Robust Hypothesis Testing","Distributional Robustness","Multi-Player Multi-Armed Bandits","Adversarial Robustness"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng","en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Akshayaa Magesh"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129164"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["There is a rich literature of algorithms for inference, prediction, and decision-making problems when the underlying distributions governing the data are known and well-modeled. The research from the past few decades has provided powerful learning algorithms when such distributions cannot be easily modeled, for instance with high dimensional data. As a result, such data driven methods are becoming ubiquitous in a wide variety of real-life applications, including safety-critical ones such as self-driving and medical diagnosis. In order for the reliable and safe deployment of such algorithms in practice, there exist several imminent questions to be answered. In this dissertation, a few topics in robustness of inference and learning methods are studied. One of the key issues with data-driven methods in practice is unexpected changes that can occur at inference time potentially affecting the performance of these methods, for instance, deviations in the data generating distributions, irrelevant or unrecognizable inputs, and adversarial attacks from unknown sources. The underlying theme connecting the topics studied in this dissertation is the development of learning algorithms robust to such unexpected, potentially harmful, deviations. Broadly, three problems in robust inference and learning are discussed in this dissertation - out-of-distribution detection for machine learning models, detection robust to distribution shifts, and multi-player multi-armed bandits robust to adversarial attacks. Principled approaches for these problems with theoretical guarantees are derived using tools from statistics, information theory and optimization, that are practical, resilient and efficiently implementable.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","The student, Akshayaa Magesh, accepted the attached license on 2025-02-04 at 04:25.","The student, Akshayaa Magesh, submitted this Dissertation for approval on 2025-02-04 at 04:43.","This Dissertation was approved for publication on 2025-02-07 at 12:49.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21630 on 2025-10-19 at 18:08:41"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Certifying robustness in inference and learning problems"]}]}],"canonical_facts":{"dc:contributor":["Veeravalli, Venugopal V.","Rayadurgam, Srikant","Raginsky, Maxim","Shomorony, Ilan"],"dc:creator":["Magesh, Akshayaa"],"dc:date":["2025-02-07","2025-05"],"dc:description":["There is a rich literature of algorithms for inference, prediction, and decision-making problems when the underlying distributions governing the data are known and well-modeled. The research from the past few decades has provided powerful learning algorithms when such distributions cannot be easily modeled, for instance with high dimensional data. As a result, such data driven methods are becoming ubiquitous in a wide variety of real-life applications, including safety-critical ones such as self-driving and medical diagnosis. In order for the reliable and safe deployment of such algorithms in practice, there exist several imminent questions to be answered. In this dissertation, a few topics in robustness of inference and learning methods are studied. One of the key issues with data-driven methods in practice is unexpected changes that can occur at inference time potentially affecting the performance of these methods, for instance, deviations in the data generating distributions, irrelevant or unrecognizable inputs, and adversarial attacks from unknown sources. The underlying theme connecting the topics studied in this dissertation is the development of learning algorithms robust to such unexpected, potentially harmful, deviations. Broadly, three problems in robust inference and learning are discussed in this dissertation - out-of-distribution detection for machine learning models, detection robust to distribution shifts, and multi-player multi-armed bandits robust to adversarial attacks. Principled approaches for these problems with theoretical guarantees are derived using tools from statistics, information theory and optimization, that are practical, resilient and efficiently implementable.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","The student, Akshayaa Magesh, accepted the attached license on 2025-02-04 at 04:25.","The student, Akshayaa Magesh, submitted this Dissertation for approval on 2025-02-04 at 04:43.","This Dissertation was approved for publication on 2025-02-07 at 12:49.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21630 on 2025-10-19 at 18:08:41"],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129164"],"dc:language":["eng","en"],"dc:rights":["Copyright 2025 Akshayaa Magesh"],"dc:subject":["Out-of-Distribution Detection","Robust Hypothesis Testing","Distributional Robustness","Multi-Player Multi-Armed Bandits","Adversarial Robustness"],"dc:title":["Certifying robustness in inference and learning problems"],"dc:type":["Thesis","text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:04Z"}