본문

서브메뉴

Topics in Geometric Deep Learning and Learning on Manifolds
Topics in Geometric Deep Learning and Learning on Manifolds
Topics in Geometric Deep Learning and Learning on Manifolds

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202103600
ISBN  
9798315721338
DDC  
519
저자명  
Chew, Joyce Allison.
서명/저자  
Topics in Geometric Deep Learning and Learning on Manifolds
발행사항  
[Sl] : University of California, Los Angeles, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
232 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-11, Section: A.
주기사항  
Advisor: Needell, Deanna M.
학위논문주기  
Thesis (Ph.D.)--University of California, Los Angeles, 2025.
초록/해제  
요약In this thesis, we discuss three topics in geometric deep learning and learning on manifolds. First, we study the geometric scattering transform, which is a wavelet-based transform defined on non-Euclidean domains such as graphs and manifolds. We introduce a framework for constructing and analyzing geometric scattering transforms on general measure spaces, and we propose methods for implementing a manifold scattering transform given only point-cloud data. We provide convergence analysis of one such method, and we perform numerical experiments on real-world data to validate the methods' utility. Next, we apply our framework to directed graphs and define a new scattering transform. We propose using an autoencoder to compress the scattering coefficients for better performance on downstream tasks, such as inference of cellular signaling networks. We experimentally demonstrate the merits of our methods on several data sets. The second main topic of this thesis is the design and analysis of manifold neural networks. We study a class of manifold neural networks implemented solely on point-cloud data sampled uniformly at random from an unknown manifold and prove that the outputs of such networks converge to their continuum counterparts. We supply a quantitative rate of convergence, and we experimentally investigate the sharpness of our rate. Next, we propose a framework for designing broad classes of manifold neural networks, and we prove convergence rates for such networks under nonuniform random sampling assumptions. We experimentally evaluate several architectures on synthetic data and single-cell RNA sequencing data. The final topic of this thesis is low-rank approximation of manifold-valued data. We propose an adaptation of nonnegative matrix factorization to manifold-valued data. We derive alternating updates for computing this factorization and apply our method to diffusion tensor magnetic resonance imaging data. The work in this thesis demonstrates ways in which geometric structure in data domains may be incorporated in the design and study of new data analysis tools.
일반주제명  
Applied mathematics
일반주제명  
Information science
키워드  
Geometric deep learning
키워드  
Low-rank approximation
키워드  
Manifold hypothesis
키워드  
Manifold neural networks
키워드  
Manifold-valued data
기타저자  
University of California, Los Angeles Mathematics 0540
기본자료저록  
Dissertations Abstracts International. 86-11A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017357788
■00520260202103600
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798315721338
■035    ▼a(MiAaPQ)AAI32042428
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a519
■1001  ▼aChew,  Joyce  Allison.
■24510▼aTopics  in  Geometric  Deep  Learning  and  Learning  on  Manifolds
■260    ▼a[Sl]▼bUniversity  of  California,  Los  Angeles▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a232  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-11,  Section:  A.
■500    ▼aAdvisor:  Needell,  Deanna  M.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Los  Angeles,  2025.
■520    ▼aIn  this  thesis,  we  discuss  three  topics  in  geometric  deep  learning  and  learning  on  manifolds.  First,  we  study  the  geometric  scattering  transform,  which  is  a  wavelet-based  transform  defined  on  non-Euclidean  domains  such  as  graphs  and  manifolds.  We  introduce  a  framework  for  constructing  and  analyzing  geometric  scattering  transforms  on  general  measure  spaces,  and  we  propose  methods  for  implementing  a  manifold  scattering  transform  given  only  point-cloud  data.  We  provide  convergence  analysis  of  one  such  method,  and  we  perform  numerical  experiments  on  real-world  data  to  validate  the  methods'  utility.  Next,  we  apply  our  framework  to  directed  graphs  and  define  a  new  scattering  transform.  We  propose  using  an  autoencoder  to  compress  the  scattering  coefficients  for  better  performance  on  downstream  tasks,  such  as  inference  of  cellular  signaling  networks.  We  experimentally  demonstrate  the  merits  of  our  methods  on  several  data  sets.  The  second  main  topic  of  this  thesis  is  the  design  and  analysis  of  manifold  neural  networks.  We  study  a  class  of  manifold  neural  networks  implemented  solely  on  point-cloud  data  sampled  uniformly  at  random  from  an  unknown  manifold  and  prove  that  the  outputs  of  such  networks  converge  to  their  continuum  counterparts.  We  supply  a  quantitative  rate  of  convergence,  and  we  experimentally  investigate  the  sharpness  of  our  rate.  Next,  we  propose  a  framework  for  designing  broad  classes  of  manifold  neural  networks,  and  we  prove  convergence  rates  for  such  networks  under  nonuniform  random  sampling  assumptions.  We  experimentally  evaluate  several  architectures  on  synthetic  data  and  single-cell  RNA  sequencing  data.  The  final  topic  of  this  thesis  is  low-rank  approximation  of  manifold-valued  data.  We  propose  an  adaptation  of  nonnegative  matrix  factorization  to  manifold-valued  data.  We  derive  alternating  updates  for  computing  this  factorization  and  apply  our  method  to  diffusion  tensor  magnetic  resonance  imaging  data.  The  work  in  this  thesis  demonstrates  ways  in  which  geometric  structure  in  data  domains  may  be  incorporated  in  the  design  and  study  of  new  data  analysis  tools.
■590    ▼aSchool  code:  0031.
■650  4▼aApplied  mathematics
■650  4▼aInformation  science
■653    ▼aGeometric  deep  learning
■653    ▼aLow-rank  approximation
■653    ▼aManifold  hypothesis
■653    ▼aManifold  neural  networks
■653    ▼aManifold-valued  data
■690    ▼a0364
■690    ▼a0723
■71020▼aUniversity  of  California,  Los  Angeles▼bMathematics  0540.
■7730  ▼tDissertations  Abstracts  International▼g86-11A.
■790    ▼a0031
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357788▼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
    TF19377 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.