본문

서브메뉴

Novel First-Order Methods for Bilevel and Minimax Optimization
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
키워드  
Bilevel optimization
키워드  
First-order methods
키워드  
Minimax optimization
키워드  
Operation complexity
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


    New Books MORE
    Statistics for the past 3 years. Go to brief

    detalle info

    • Reserva
    • No existe
    • Mi carpeta
    • Primera solicitud
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    Material
    número de libro número de llamada Ubicación estado Prestar info
    TF15045 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Las reservas están disponibles en el libro de préstamos. Para hacer reservaciones, haga clic en el botón de reserva

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.