본문

서브메뉴

Bounded Subgradient Trajectories in Semialgebraic Optimization
Bounded Subgradient Trajectories in Semialgebraic Optimization
Bounded Subgradient Trajectories in Semialgebraic Optimization

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202103142
ISBN  
9798314886533
DDC  
519
저자명  
Li, Xiaopeng.
서명/저자  
Bounded Subgradient Trajectories in Semialgebraic Optimization
발행사항  
[Sl] : Columbia University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
186 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
주기사항  
Advisor: Josz, Cedric.
학위논문주기  
Thesis (Ph.D.)--Columbia University, 2025.
초록/해제  
요약Solving modern data science problems relies on optimization algorithms that often succeed in high-dimensional, large-scale settings. First-order methods, in particular, are widely used due to their low per-iteration cost and scalability. However, despite their empirical success, theoretical understanding of their behavior in such settings remains limited. Classical optimization theory is typically built on assumptions about the objective function, such as convexity, smoothness, and coercivity, which are rarely satisfied in practice. In addition, common assumptions on algorithms, such as the boundedness of iterates or the existence of limit points, are often difficult to verify. To address these challenges, we develop a framework that replaces these assumptions with easily checkable conditions, using tools from dynamical systems, semialgebraic geometry, and variational analysis.A key result of this thesis is that a broad class of optimization problems, including phase retrieval, matrix sensing, and neural networks, have bounded gradient flows. This property is central to multiple aspects of optimization. For landscape analysis, we develop practical tools for certifying the absence of bad local minima at infinity. For first-order algorithms, we analyze momentum methods and the proximal random reshuffling algorithm, proving global convergence of iterates and establishing improved convergence rates.
일반주제명  
Applied mathematics
일반주제명  
Engineering
키워드  
Data science
키워드  
Deep learning
키워드  
Dynamical system
키워드  
Machine learning
키워드  
Nonconvex optimization
키워드  
Real algebraic geometry
기타저자  
Columbia University Operations Research
기본자료저록  
Dissertations Abstracts International. 86-11B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017357168
■00520260202103142
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798314886533
■035    ▼a(MiAaPQ)AAI31994503
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a519
■1001  ▼aLi,  Xiaopeng.
■24510▼aBounded  Subgradient  Trajectories  in  Semialgebraic  Optimization
■260    ▼a[Sl]▼bColumbia  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a186  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-11,  Section:  B.
■500    ▼aAdvisor:  Josz,  Cedric.
■5021  ▼aThesis  (Ph.D.)--Columbia  University,  2025.
■520    ▼aSolving  modern  data  science  problems  relies  on  optimization  algorithms  that  often  succeed  in  high-dimensional,  large-scale  settings.  First-order  methods,  in  particular,  are  widely  used  due  to  their  low  per-iteration  cost  and  scalability.  However,  despite  their  empirical  success,  theoretical  understanding  of  their  behavior  in  such  settings  remains  limited.  Classical  optimization  theory  is  typically  built  on  assumptions  about  the  objective  function,  such  as  convexity,  smoothness,  and  coercivity,  which  are  rarely  satisfied  in  practice.  In  addition,  common  assumptions  on  algorithms,  such  as  the  boundedness  of  iterates  or  the  existence  of  limit  points,  are  often  difficult  to  verify.  To  address  these  challenges,  we  develop  a  framework  that  replaces  these  assumptions  with  easily  checkable  conditions,  using  tools  from  dynamical  systems,  semialgebraic  geometry,  and  variational  analysis.A  key  result  of  this  thesis  is  that  a  broad  class  of  optimization  problems,  including  phase  retrieval,  matrix  sensing,  and  neural  networks,  have  bounded  gradient  flows.  This  property  is  central  to  multiple  aspects  of  optimization.  For  landscape  analysis,  we  develop  practical  tools  for  certifying  the  absence  of  bad  local  minima  at  infinity.  For  first-order  algorithms,  we  analyze  momentum  methods  and  the  proximal  random  reshuffling  algorithm,  proving  global  convergence  of  iterates  and  establishing  improved  convergence  rates.
■590    ▼aSchool  code:  0054.
■650  4▼aApplied  mathematics
■650  4▼aEngineering
■653    ▼aData  science
■653    ▼aDeep  learning
■653    ▼aDynamical  system
■653    ▼aMachine  learning
■653    ▼aNonconvex  optimization
■653    ▼aReal  algebraic  geometry
■690    ▼a0796
■690    ▼a0364
■690    ▼a0537
■71020▼aColumbia  University▼bOperations  Research.
■7730  ▼tDissertations  Abstracts  International▼g86-11B.
■790    ▼a0054
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357168▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF18521 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.