서브메뉴
검색
Novel First-Order Methods for Bilevel and Minimax Optimization
Novel First-Order Methods for Bilevel and Minimax Optimization
Detailed Information
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202103613
- ISBN
- 9798286442799
- DDC
- 519
- 저자명
- Mei, Sanyou.
- 서명/저자
- Novel First-Order Methods for Bilevel and Minimax Optimization
- 발행사항
- [Sl] : University of Minnesota, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 199 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
- 주기사항
- Advisor: Lu, Zhaosong.
- 학위논문주기
- Thesis (Ph.D.)--University of Minnesota, 2025.
- 초록/해제
- 요약Bilevel and minimax optimization problems arise in various fields, including machine learning, game theory, and decision science. This thesis highlights the underlying connections between constrained minimax and bilevel optimization and develops novel first-order methods with strong theoretical guarantees for solving both classes of problems.Specifically, we study a class of constrained minimax problems and propose efficient augmented Lagrangian methods with complexity guarantees for both nonconvex-concave and nonconvex-strongly-concave objective functions. We then show that bilevel optimization can be approximately reformulated as a minimax problem and introduce first-order penalty methods with provable complexity guarantees. Additionally, we propose a sequential minimax optimization method for solving a class of constrained bilevel problems and establish corresponding complexity results. Preliminary numerical experiments demonstrate the effectiveness of the proposed methods.
- 일반주제명
- Applied mathematics
- 기타저자
- University of Minnesota Industrial and Systems Engineering
- 기본자료저록
- Dissertations Abstracts International. 86-12B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017357881
■00520260202103613
■006m o d
■007cr#unu||||||||
■020 ▼a9798286442799
■035 ▼a(MiAaPQ)AAI32043728
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a519
■1001 ▼aMei, Sanyou.
■24510▼aNovel First-Order Methods for Bilevel and Minimax Optimization
■260 ▼a[Sl]▼bUniversity of Minnesota▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a199 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-12, Section: B.
■500 ▼aAdvisor: Lu, Zhaosong.
■5021 ▼aThesis (Ph.D.)--University of Minnesota, 2025.
■520 ▼aBilevel and minimax optimization problems arise in various fields, including machine learning, game theory, and decision science. This thesis highlights the underlying connections between constrained minimax and bilevel optimization and develops novel first-order methods with strong theoretical guarantees for solving both classes of problems.Specifically, we study a class of constrained minimax problems and propose efficient augmented Lagrangian methods with complexity guarantees for both nonconvex-concave and nonconvex-strongly-concave objective functions. We then show that bilevel optimization can be approximately reformulated as a minimax problem and introduce first-order penalty methods with provable complexity guarantees. Additionally, we propose a sequential minimax optimization method for solving a class of constrained bilevel problems and establish corresponding complexity results. Preliminary numerical experiments demonstrate the effectiveness of the proposed methods.
■590 ▼aSchool code: 0130.
■650 4▼aApplied mathematics
■653 ▼aBilevel optimization
■653 ▼aFirst-order methods
■653 ▼aMinimax optimization
■653 ▼aOperation complexity
■690 ▼a0796
■690 ▼a0364
■71020▼aUniversity of Minnesota▼bIndustrial and Systems Engineering.
■7730 ▼tDissertations Abstracts International▼g86-12B.
■790 ▼a0130
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357881▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
Preview
Export
ChatGPT Discussion
AI Recommended Related Books
detalle info
- Reserva
- No existe
- Mi carpeta
- Primera solicitud
- Non-Book Loan Application
- Nighttime Book Loan Application
Available after logging in.


