본문

서브메뉴

Advancing Computations for Wasserstein Gradient Flows
Advancing Computations for Wasserstein Gradient Flows
Advancing Computations for Wasserstein Gradient Flows

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105305
ISBN  
9798265435071
DDC  
519
저자명  
Zuo, Xinzhe.
서명/저자  
Advancing Computations for Wasserstein Gradient Flows
발행사항  
[Sl] : University of California, Los Angeles, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
198 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: Osher, Stanley J.
학위논문주기  
Thesis (Ph.D.)--University of California, Los Angeles, 2025.
초록/해제  
요약Wasserstein gradient flows have emerged as a powerful mathematical framework that unifies optimization, sampling, and the dynamics of probability distributions. Rooted in optimal transport theory, they describe the steepest descent of energy functionals in the space of probability measures, providing deep geometric insight into algorithms used across machine learning, scientific computing, and statistical physics. As applications grow in scale and complexity, however, advancing the computational frontiers of Wasserstein gradient flows demands both new algorithmic formulations and rigorous numerical analysis. This dissertation aims to address these challenges by developing efficient, theoretically grounded methods that connect optimization dynamics, neural approximation, and stochastic sampling within the Wasserstein framework.We first propose Primal-Dual Damping (PDD) algorithms for optimization, which generalize the primal-dual hybrid gradient method and reveal a continuous-time limit governed by second-order dynamics that extend heavy-ball and Hessian-driven damping systems. Next, we analyze neural network-projected schemes for approximating one-dimensional Wasserstein gradient flows, establishing well-posedness, consistency, and error bounds for their neural representations and validating them on canonical PDEs such as Fokker-Planck and porous medium equations. Finally, we introduce Gradient-Adjusted Underdamped Langevin (GAUL) dynamics, which incorporate PDD mechanisms from optimization into stochastic sampling to achieve faster convergence toward target distributions. Together, these works contribute to both the theory and computation of Wasserstein gradient flows, bridging optimization, PDE, and sampling through a unified and rigorous mathematical perspective.
일반주제명  
Applied mathematics
일반주제명  
Mathematics
일반주제명  
Computer science
키워드  
Optimal transport theory
키워드  
Primal-Dual Damping
키워드  
Algorithmic formulations
키워드  
Wasserstein gradient flows
기타저자  
University of California, Los Angeles Mathematics 0540
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017360109
■00520260202105305
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798265435071
■035    ▼a(MiAaPQ)AAI32283108
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a519
■1001  ▼aZuo,  Xinzhe.
■24510▼aAdvancing  Computations  for  Wasserstein  Gradient  Flows
■260    ▼a[Sl]▼bUniversity  of  California,  Los  Angeles▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a198  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  Osher,  Stanley  J.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Los  Angeles,  2025.
■520    ▼aWasserstein  gradient  flows  have  emerged  as  a  powerful  mathematical  framework  that  unifies  optimization,  sampling,  and  the  dynamics  of  probability  distributions.  Rooted  in  optimal  transport  theory,  they  describe  the  steepest  descent  of  energy  functionals  in  the  space  of  probability  measures,  providing  deep  geometric  insight  into  algorithms  used  across  machine  learning,  scientific  computing,  and  statistical  physics.  As  applications  grow  in  scale  and  complexity,  however,  advancing  the  computational  frontiers  of  Wasserstein  gradient  flows  demands  both  new  algorithmic  formulations  and  rigorous  numerical  analysis.  This  dissertation  aims  to  address  these  challenges  by  developing  efficient,  theoretically  grounded  methods  that  connect  optimization  dynamics,  neural  approximation,  and  stochastic  sampling  within  the  Wasserstein  framework.We  first  propose  Primal-Dual  Damping  (PDD)  algorithms  for  optimization,  which  generalize  the  primal-dual  hybrid  gradient  method  and  reveal  a  continuous-time  limit  governed  by  second-order  dynamics  that  extend  heavy-ball  and  Hessian-driven  damping  systems.  Next,  we  analyze  neural  network-projected  schemes  for  approximating  one-dimensional  Wasserstein  gradient  flows,  establishing  well-posedness,  consistency,  and  error  bounds  for  their  neural  representations  and  validating  them  on  canonical  PDEs  such  as  Fokker-Planck  and  porous  medium  equations.  Finally,  we  introduce  Gradient-Adjusted  Underdamped  Langevin  (GAUL)  dynamics,  which  incorporate  PDD  mechanisms  from  optimization  into  stochastic  sampling  to  achieve  faster  convergence  toward  target  distributions.  Together,  these  works  contribute  to  both  the  theory  and  computation  of  Wasserstein  gradient  flows,  bridging  optimization,  PDE,  and  sampling  through  a  unified  and  rigorous  mathematical  perspective.
■590    ▼aSchool  code:  0031.
■650  4▼aApplied  mathematics
■650  4▼aMathematics
■650  4▼aComputer  science
■653    ▼aOptimal  transport  theory
■653    ▼aPrimal-Dual  Damping
■653    ▼aAlgorithmic  formulations
■653    ▼aWasserstein  gradient  flows
■690    ▼a0364
■690    ▼a0984
■690    ▼a0405
■71020▼aUniversity  of  California,  Los  Angeles▼bMathematics  0540.
■7730  ▼tDissertations  Abstracts  International▼g87-05B.
■790    ▼a0031
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360109▼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
    TF16496 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.