{"id":{"repo_id":"nus","oai_identifier":"oai:scholarbank.nus.edu.sg:10635/311246"},"canonical_url":"https://search.dev.ndltd.org/etd/nus/oai:scholarbank.nus.edu.sg:10635/311246","repository":{"repo_id":"nus","name":"National University of Singapore","base_url":"https://scholarbank.nus.edu.sg/oai/request"},"display":{"title":"TOWARDS EFFICIENT LARGE-SCALE BI-LEVEL OPTIMIZATION, ALGORITHMS AND APPLICATIONS","abstract":"Bi-level optimization is a mathematical framework with a long history of research, dealing with hierarchical optimization problems where one problem is nested within the other. Recently, with the rise of machine learning, bi-level optimization has regained attention as a theoretical framework covering a wide range of machine learning problems, including hyperparameter optimization, neural architecture search, robust machine learning, meta-learning, and physics-informed machine learning. In recent years, as the scale of machine learning problems has grown rapidly, large-scale bi-level optimization has emerged as a critical area of study. These large-scale settings bring unique computational and algorithmic challenges, including memory constraints, scalability issues, and the complexity of high-order gradient computations. This thesis focuses on analyzing the key challenges introduced by large-scale bi-level optimization and presents recent methodological advances aimed at addressing them. Beyond a survey of existing approaches, we propose principled algorithmic designs tailored to various problem scenarios, enabling the efficient resolution of large-scale bi-level optimization tasks in practical applications. These contributions aim to bridge the gap between theoretical developments and scalable deployment in real-world machine learning systems.","abstract_html":"Bi-level optimization is a mathematical framework with a long history of research, dealing with hierarchical optimization problems where one problem is nested within the other. Recently, with the rise of machine learning, bi-level optimization has regained attention as a theoretical framework covering a wide range of machine learning problems, including hyperparameter optimization, neural architecture search, robust machine learning, meta-learning, and physics-informed machine learning. In recent years, as the scale of machine learning problems has grown rapidly, large-scale bi-level optimization has emerged as a critical area of study. These large-scale settings bring unique computational and algorithmic challenges, including memory constraints, scalability issues, and the complexity of high-order gradient computations. This thesis focuses on analyzing the key challenges introduced by large-scale bi-level optimization and presents recent methodological advances aimed at addressing them. Beyond a survey of existing approaches, we propose principled algorithmic designs tailored to various problem scenarios, enabling the efficient resolution of large-scale bi-level optimization tasks in practical applications. These contributions aim to bridge the gap between theoretical developments and scalable deployment in real-world machine learning systems.","abstract_has_math":false,"creators":["SHEN QIANLI"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05-19","date_published":"2025-05-19","updated_at":"2026-07-24T03:30:34Z","subjects":["machine learning","large-scale","bi-level Optimization"],"languages":[],"rights":[],"rights_urls":["https://scholarbank.nus.edu.sg/bitstreams/552b8cef-27ff-4174-9661-6df57fdc733c/download"],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["SHEN QIANLI"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2025-05-19"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://scholarbank.nus.edu.sg/handle/10635/311246"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["machine learning","large-scale","bi-level Optimization"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["https://scholarbank.nus.edu.sg/bitstreams/552b8cef-27ff-4174-9661-6df57fdc733c/download"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://scholarbank.nus.edu.sg/bitstreams/487408c3-0c3c-4230-aad6-fbd380d8c9e9/download"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Bi-level optimization is a mathematical framework with a long history of research, dealing with hierarchical optimization problems where one problem is nested within the other. Recently, with the rise of machine learning, bi-level optimization has regained attention as a theoretical framework covering a wide range of machine learning problems, including hyperparameter optimization, neural architecture search, robust machine learning, meta-learning, and physics-informed machine learning. In recent years, as the scale of machine learning problems has grown rapidly, large-scale bi-level optimization has emerged as a critical area of study. These large-scale settings bring unique computational and algorithmic challenges, including memory constraints, scalability issues, and the complexity of high-order gradient computations. This thesis focuses on analyzing the key challenges introduced by large-scale bi-level optimization and presents recent methodological advances aimed at addressing them. Beyond a survey of existing approaches, we propose principled algorithmic designs tailored to various problem scenarios, enabling the efficient resolution of large-scale bi-level optimization tasks in practical applications. These contributions aim to bridge the gap between theoretical developments and scalable deployment in real-world machine learning systems."]},{"key":"dc:format.checksum.md5","label":"Dc Format Checksum Md5","values":["9f3c6f2aa8f96291ef77b0a18484521d","ef2348338750c030d8a8847bcfccf6ee","c5f176f0628ab9ee4bf114f565e05484"]},{"key":"dc:title","label":"Title","values":["TOWARDS EFFICIENT LARGE-SCALE BI-LEVEL OPTIMIZATION, ALGORITHMS AND APPLICATIONS"]}]}],"canonical_facts":{"dc:creator":["SHEN QIANLI"],"dc:date.issued":["2025-05-19"],"dc:description.abstract":["Bi-level optimization is a mathematical framework with a long history of research, dealing with hierarchical optimization problems where one problem is nested within the other. Recently, with the rise of machine learning, bi-level optimization has regained attention as a theoretical framework covering a wide range of machine learning problems, including hyperparameter optimization, neural architecture search, robust machine learning, meta-learning, and physics-informed machine learning. In recent years, as the scale of machine learning problems has grown rapidly, large-scale bi-level optimization has emerged as a critical area of study. These large-scale settings bring unique computational and algorithmic challenges, including memory constraints, scalability issues, and the complexity of high-order gradient computations. This thesis focuses on analyzing the key challenges introduced by large-scale bi-level optimization and presents recent methodological advances aimed at addressing them. Beyond a survey of existing approaches, we propose principled algorithmic designs tailored to various problem scenarios, enabling the efficient resolution of large-scale bi-level optimization tasks in practical applications. These contributions aim to bridge the gap between theoretical developments and scalable deployment in real-world machine learning systems."],"dc:format.checksum.md5":["9f3c6f2aa8f96291ef77b0a18484521d","ef2348338750c030d8a8847bcfccf6ee","c5f176f0628ab9ee4bf114f565e05484"],"dc:identifier.uri":["https://scholarbank.nus.edu.sg/bitstreams/487408c3-0c3c-4230-aad6-fbd380d8c9e9/download"],"dc:relation.isreferencedby":["https://scholarbank.nus.edu.sg/handle/10635/311246"],"dc:rights":["https://scholarbank.nus.edu.sg/bitstreams/552b8cef-27ff-4174-9661-6df57fdc733c/download"],"dc:subject":["machine learning","large-scale","bi-level Optimization"],"dc:title":["TOWARDS EFFICIENT LARGE-SCALE BI-LEVEL OPTIMIZATION, ALGORITHMS AND APPLICATIONS"],"dc:type":["Thesis"]},"updated_at":"2026-07-24T03:30:34Z"}