본문

서브메뉴

Learning and Inference for Distributions: from Optimal Transport to Markov Chain Monte Carlo
Learning and Inference for Distributions: from Optimal Transport to Markov Chain Monte Car...
Learning and Inference for Distributions: from Optimal Transport to Markov Chain Monte Carlo

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105516
ISBN  
9798263343286
DDC  
515
저자명  
Fan, Jiaojiao.
서명/저자  
Learning and Inference for Distributions: from Optimal Transport to Markov Chain Monte Carlo
발행사항  
[Sl] : Georgia Institute of Technology, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
134 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: Chen, Yongxin.
학위논문주기  
Thesis (Ph.D.)--Georgia Institute of Technology, 2024.
초록/해제  
요약Distributional data refers to data that provides insights into the probability distribution of a random variable or a set of random variables. In the machine learning (ML) domain, distributions are typically represented by a large number of samples. They have numer-ous crucial applications across various fields, including computer vision, healthcare and biomedical engineering. There is a famous quote: "Data is the food for machine learn-ing." Understanding how to transform and manipulate distributions in high-dimensional and data-driven formats is therefore essential. This dissertation focuses on large-scale dis-tributional problems, characterized either by the sheer volume of data or by high dimen-sionality.We investigate two fundamental mathematical tools: optimal transport and Markov Chain Monte Carlo (MCMC) sampling, both of which are integral to the transformation and manipulation of distributional data. Optimal transport is a centuries-old mathematical framework for comparing probability distributions. One of its most significant concepts, the Wasserstein distance, has had a substantial impact on machine learning, particularly in the study of Generative Adversarial Networks. Despite its important applications, such as calculating distribution discrepancies, interpolating, and aligning distributions, optimal transport is often hindered by its computational cost. In this thesis, we improve the com-putational efficiency of optimal transport from two perspectives. First, for discrete optimal transport (OT), where probability distributions are represented by probability vectors, we enhance the multi-marginal optimal transport (MOT) associated with graph structures. Sec-ond, we scale up OT to handle millions of samples by introducing neural OT solvers. Ad-ditionally, we demonstrate multiple downstream applications for these neural OT solvers, including Wasserstein gradient flow, Wasserstein barycenter and generalized geodesic.MCMC sampling remains the primary technique for sampling from a distribution and has numerous applications in Bayesian statistics, computational physics, and computationalbiology. However, it faces challenges in terms of computational scalability, particularly with increasing dimensions. To overcome these limitations, we introduce a novel algo-rithm based on the proximal sampler, and rigorously prove its computational complexity for converging to the target distribution. Additionally, we prove a Gaussian concentration inequality for semi-smooth functions, which could be of independent interest. This re-sult recovers the order of the well-known Gaussian concentration inequality for Lipschitz functions.
일반주제명  
Convex analysis
일반주제명  
Probability
일반주제명  
Visualization
일반주제명  
Entropy
일반주제명  
Neural networks
일반주제명  
Markov analysis
일반주제명  
Computer science
일반주제명  
Mathematics
기타저자  
Georgia Institute of Technology.
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2024        us                              c    eng  d
■001000017360389
■00520260202105516
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798263343286
■035    ▼a(MiAaPQ)AAI32309367
■035    ▼a(MiAaPQ)GeorgiaTech75659
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a515
■1001  ▼aFan,  Jiaojiao.
■24510▼aLearning  and  Inference  for  Distributions:  from  Optimal  Transport  to  Markov  Chain  Monte  Carlo
■260    ▼a[Sl]▼bGeorgia  Institute  of  Technology▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a134  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  Chen,  Yongxin.
■5021  ▼aThesis  (Ph.D.)--Georgia  Institute  of  Technology,  2024.
■520    ▼aDistributional  data  refers  to  data  that  provides  insights  into  the  probability  distribution  of  a  random  variable  or  a  set  of  random  variables.  In  the  machine  learning  (ML)  domain,  distributions  are  typically  represented  by  a  large  number  of  samples.  They  have  numer-ous  crucial  applications  across  various  fields,  including  computer  vision,  healthcare  and  biomedical  engineering.  There  is  a  famous  quote:  "Data  is  the  food  for  machine  learn-ing."  Understanding  how  to  transform  and  manipulate  distributions  in  high-dimensional  and  data-driven  formats  is  therefore  essential.  This  dissertation  focuses  on  large-scale  dis-tributional  problems,  characterized  either  by  the  sheer  volume  of  data  or  by  high  dimen-sionality.We  investigate  two  fundamental  mathematical  tools:  optimal  transport  and  Markov  Chain  Monte  Carlo  (MCMC)  sampling,  both  of  which  are  integral  to  the  transformation  and  manipulation  of  distributional  data.  Optimal  transport  is  a  centuries-old  mathematical  framework  for  comparing  probability  distributions.  One  of  its  most  significant  concepts,  the  Wasserstein  distance,  has  had  a  substantial  impact  on  machine  learning,  particularly  in  the  study  of  Generative  Adversarial  Networks.  Despite  its  important  applications,  such  as  calculating  distribution  discrepancies,  interpolating,  and  aligning  distributions,  optimal  transport  is  often  hindered  by  its  computational  cost.  In  this  thesis,  we  improve  the  com-putational  efficiency  of  optimal  transport  from  two  perspectives.  First,  for  discrete  optimal  transport  (OT),  where  probability  distributions  are  represented  by  probability  vectors,  we  enhance  the  multi-marginal  optimal  transport  (MOT)  associated  with  graph  structures.  Sec-ond,  we  scale  up  OT  to  handle  millions  of  samples  by  introducing  neural  OT  solvers.  Ad-ditionally,  we  demonstrate  multiple  downstream  applications  for  these  neural  OT  solvers,  including  Wasserstein  gradient  flow,  Wasserstein  barycenter  and  generalized  geodesic.MCMC  sampling  remains  the  primary  technique  for  sampling  from  a  distribution  and  has  numerous  applications  in  Bayesian  statistics,  computational  physics,  and  computationalbiology.  However,  it  faces  challenges  in  terms  of  computational  scalability,  particularly  with  increasing  dimensions.  To  overcome  these  limitations,  we  introduce  a  novel  algo-rithm  based  on  the  proximal  sampler,  and  rigorously  prove  its  computational  complexity  for  converging  to  the  target  distribution.  Additionally,  we  prove  a  Gaussian  concentration  inequality  for  semi-smooth  functions,  which  could  be  of  independent  interest.  This  re-sult  recovers  the  order  of  the  well-known  Gaussian  concentration  inequality  for  Lipschitz  functions.
■590    ▼aSchool  code:  0078.
■650  4▼aConvex  analysis
■650  4▼aProbability
■650  4▼aVisualization
■650  4▼aEntropy
■650  4▼aNeural  networks
■650  4▼aMarkov  analysis
■650  4▼aComputer  science
■650  4▼aMathematics
■690    ▼a0984
■690    ▼a0800
■690    ▼a0405
■690    ▼a0796
■71020▼aGeorgia  Institute  of  Technology.
■7730  ▼tDissertations  Abstracts  International▼g87-05B.
■790    ▼a0078
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360389▼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
    TF17130 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.