본문

서브메뉴

Structured Statistical Estimation Via Optimization
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
기타저자  
Georgia Institute of Technology.
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.

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
    TF14628 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.