본문

서브메뉴

Statistical and Algorithmic Perspectives on Estimating Optimal Transport Maps
Statistical and Algorithmic Perspectives on Estimating Optimal Transport Maps
Statistical and Algorithmic Perspectives on Estimating Optimal Transport Maps

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202104704
ISBN  
9798293886982
DDC  
519
저자명  
Pooladian, Aram-Alexandre.
서명/저자  
Statistical and Algorithmic Perspectives on Estimating Optimal Transport Maps
발행사항  
[Sl] : New York University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
318 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
주기사항  
Advisor: Niles-Weed, Jonthan.
학위논문주기  
Thesis (Ph.D.)--New York University, 2025.
초록/해제  
요약Optimal transport maps, or Brenier maps, have become widely adopted in data-driven domains as they provide a canonical transformation between independent datasets. While many existing methods aim for optimal statistical performance, they often fall short in practical regimes of interest, such as when the data is high-dimensional or when the sample size is large. In this thesis, we analyze principled algorithms for estimating optimal transport maps in precisely these regimes. Our rst contribution is the introduction of the entropic Brenier map, an estimator of the Brenier map based on entropic optimal transport, which harnesses the computational eciency of Sinkhorn's matrix scaling algorithm (Sinkhorn, 1967). We prove the rst nitesample guarantees for estimating optimal transport maps using this estimator, demonstrate that it is minimax optimal in the semi-discrete setting, and make further connections to the statistical estimation of Schrodinger bridge between two distributions. Next, we further derive new theoretical properties of the entropic Brenier map, such as bounds on the Lipschitz constant of the map as well as its stability with respect to the target measures; these results also yield new insights for the unregularized optimal transport map. For our nal contribution, we propose a new optimization framework for functionals dened over a suitable family of optimal transport maps. As an application, we develop the rst gradient-based algorithm for mean-eld variational inference that comes with end-to-end convergence guarantees. 
일반주제명  
Applied mathematics
일반주제명  
Statistics
키워드  
Entropic regularization
키워드  
Non-parametric statistics
키워드  
Optimal transport
키워드  
Variational inference
기타저자  
New York University Center for Data Science
기본자료저록  
Dissertations Abstracts International. 87-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017358451
■00520260202104704
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798293886982
■035    ▼a(MiAaPQ)AAI32116765
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a519
■1001  ▼aPooladian,  Aram-Alexandre.
■24510▼aStatistical  and  Algorithmic  Perspectives  on  Estimating  Optimal  Transport  Maps
■260    ▼a[Sl]▼bNew  York  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a318  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-03,  Section:  B.
■500    ▼aAdvisor:  Niles-Weed,  Jonthan.
■5021  ▼aThesis  (Ph.D.)--New  York  University,  2025.
■520    ▼aOptimal  transport  maps,  or  Brenier  maps,  have  become  widely  adopted  in  data-driven  domains  as  they  provide  a  canonical  transformation  between  independent  datasets.  While  many  existing  methods  aim  for  optimal  statistical  performance,  they  often  fall  short  in  practical  regimes  of  interest,  such  as  when  the  data  is  high-dimensional  or  when  the  sample  size  is  large.  In  this  thesis,  we  analyze  principled  algorithms  for  estimating  optimal  transport  maps  in  precisely  these  regimes.  Our  rst  contribution  is  the  introduction  of  the  entropic  Brenier  map,  an  estimator  of  the  Brenier  map  based  on  entropic  optimal  transport,  which  harnesses  the  computational  eciency  of  Sinkhorn's  matrix  scaling  algorithm  (Sinkhorn,  1967).  We  prove  the  rst  nitesample  guarantees  for  estimating  optimal  transport  maps  using  this  estimator,  demonstrate  that  it  is  minimax  optimal  in  the  semi-discrete  setting,  and  make  further  connections  to  the  statistical  estimation  of  Schrodinger  bridge  between  two  distributions.  Next,  we  further  derive  new  theoretical  properties  of  the  entropic  Brenier  map,  such  as  bounds  on  the  Lipschitz  constant  of  the  map  as  well  as  its  stability  with  respect  to  the  target  measures;  these  results  also  yield  new  insights  for  the  unregularized  optimal  transport  map.  For  our  nal  contribution,  we  propose  a  new  optimization  framework  for  functionals  dened  over  a  suitable  family  of  optimal  transport  maps.  As  an  application,  we  develop  the  rst  gradient-based  algorithm  for  mean-eld  variational  inference  that  comes  with  end-to-end  convergence  guarantees. 
■590    ▼aSchool  code:  0146.
■650  4▼aApplied  mathematics
■650  4▼aStatistics
■653    ▼aEntropic  regularization
■653    ▼aNon-parametric  statistics
■653    ▼aOptimal  transport
■653    ▼aVariational  inference
■690    ▼a0364
■690    ▼a0463
■71020▼aNew  York  University▼bCenter  for  Data  Science.
■7730  ▼tDissertations  Abstracts  International▼g87-03B.
■790    ▼a0146
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358451▼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

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF16029 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.