서브메뉴
검색
Structured Statistical Estimation Via Optimization
Structured Statistical Estimation Via Optimization
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105537
- ISBN
- 9798263389666
- DDC
- 330
- 저자명
- McRae, Andrew D.
- 서명/저자
- Structured Statistical Estimation Via Optimization
- 발행사항
- [Sl] : Georgia Institute of Technology, 2022
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2022
- 형태사항
- 189 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-05, Section: A.
- 주기사항
- Advisor: Davenport, Mark.
- 학위논문주기
- Thesis (Ph.D.)--Georgia Institute of Technology, 2022.
- 초록/해제
- 요약This thesis shows how we can exploit low-dimensional structure in high-dimensional statistics and machine learning problems via optimization. We show several settings where, with an appropriate choice of optimization algorithm, we can perform useful estimation with a complexity that scales not with the original problem dimension but with a much smaller intrinsic dimension.In the low-rank matrix completion and denoising problems, we can exploit low-rank structure to recover a large matrix from noisy observations of some or all of its entries. We prove state-of-the-art results for this problem in the case of Poisson noise and show that these results are minimax-optimal.Next, we study the problem of recovering a sparse vector from nonlinear measurements. We present a lifted matrix framework for the sparse phase retrieval and sparse PCA problems that includes a novel atomic norm regularizer. We prove that solving certain convex optimization problems in this framework yields estimators with near-optimal performance. Although we do not know how to compute these estimators efficiently and exactly, we derive a principled heuristic algorithm for sparse phase retrieval that matches existing state-of-the-art algorithms.Third, we show how we can exploit low-dimensional manifold structure in supervised learning. In a reproducing kernel Hilbert space framework, we show that smooth functions on a manifold can be estimated with a complexity scaling with the manifold dimension rather than a larger embedding space dimension.Finally, we study the interaction between high ambient dimension and a lower intrinsic dimension in the harmless interpolation phenomenon (where learned functions generalize well despite interpolating noisy data). We present a general framework for this phenomenon in linear and reproducing kernel Hilbert space settings, proving that it occurs in many situations that previous work has not covered.
- 일반주제명
- Sparsity
- 일반주제명
- Decomposition
- 일반주제명
- Design optimization
- 일반주제명
- Recommender systems
- 일반주제명
- Optimization algorithms
- 일반주제명
- Hilbert space
- 일반주제명
- Probability distribution
- 일반주제명
- Medical research
- 일반주제명
- Information science
- 일반주제명
- Mathematics
- 일반주제명
- Medicine
- 기본자료저록
- Dissertations Abstracts International. 87-05A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2022 us c eng d■001000017360500
■00520260202105537
■006m o d
■007cr#unu||||||||
■020 ▼a9798263389666
■035 ▼a(MiAaPQ)AAI32314853
■035 ▼a(MiAaPQ)GeorgiaTech66587
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a330
■1001 ▼aMcRae, Andrew D.
■24510▼aStructured Statistical Estimation Via Optimization
■260 ▼a[Sl]▼bGeorgia Institute of Technology▼c2022
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2022
■300 ▼a189 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-05, Section: A.
■500 ▼aAdvisor: Davenport, Mark.
■5021 ▼aThesis (Ph.D.)--Georgia Institute of Technology, 2022.
■520 ▼aThis thesis shows how we can exploit low-dimensional structure in high-dimensional statistics and machine learning problems via optimization. We show several settings where, with an appropriate choice of optimization algorithm, we can perform useful estimation with a complexity that scales not with the original problem dimension but with a much smaller intrinsic dimension.In the low-rank matrix completion and denoising problems, we can exploit low-rank structure to recover a large matrix from noisy observations of some or all of its entries. We prove state-of-the-art results for this problem in the case of Poisson noise and show that these results are minimax-optimal.Next, we study the problem of recovering a sparse vector from nonlinear measurements. We present a lifted matrix framework for the sparse phase retrieval and sparse PCA problems that includes a novel atomic norm regularizer. We prove that solving certain convex optimization problems in this framework yields estimators with near-optimal performance. Although we do not know how to compute these estimators efficiently and exactly, we derive a principled heuristic algorithm for sparse phase retrieval that matches existing state-of-the-art algorithms.Third, we show how we can exploit low-dimensional manifold structure in supervised learning. In a reproducing kernel Hilbert space framework, we show that smooth functions on a manifold can be estimated with a complexity scaling with the manifold dimension rather than a larger embedding space dimension.Finally, we study the interaction between high ambient dimension and a lower intrinsic dimension in the harmless interpolation phenomenon (where learned functions generalize well despite interpolating noisy data). We present a general framework for this phenomenon in linear and reproducing kernel Hilbert space settings, proving that it occurs in many situations that previous work has not covered.
■590 ▼aSchool code: 0078.
■650 4▼aSparsity
■650 4▼aDecomposition
■650 4▼aDesign optimization
■650 4▼aRecommender systems
■650 4▼aOptimization algorithms
■650 4▼aHilbert space
■650 4▼aProbability distribution
■650 4▼aMedical research
■650 4▼aInformation science
■650 4▼aMathematics
■650 4▼aMedicine
■690 ▼a0800
■690 ▼a0723
■690 ▼a0405
■690 ▼a0564
■71020▼aGeorgia Institute of Technology.
■7730 ▼tDissertations Abstracts International▼g87-05A.
■790 ▼a0078
■791 ▼aPh.D.
■792 ▼a2022
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360500▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


