서브메뉴
검색
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
- 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
- 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.


