본문

서브메뉴

Variational Inference in High-dimensional Bayesian Regression Models
Variational Inference in High-dimensional Bayesian Regression Models
Variational Inference in High-dimensional Bayesian Regression Models

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20250211151004
ISBN  
9798382781877
DDC  
310
저자명  
Qiu, Jiaze.
서명/저자  
Variational Inference in High-dimensional Bayesian Regression Models
발행사항  
[Sl] : Harvard University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
184 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
주기사항  
Advisor: Sen, Subhabrata.
학위논문주기  
Thesis (Ph.D.)--Harvard University, 2024.
초록/해제  
요약In modern applications of Bayesian Statistics, the posterior distribution is typically high-dimensional and analytically intractable. Variational Inference (VI) has emerged as an attractive option to approximate these intractable distributions, facilitating fast, parallel computations. The simplest version of VI is the Naive Mean-field approximation (NMF), where the distribution of interest is approximated by a product distribution. In recent years, another strategy rooted in statistical physics, the Thouless-Anderson-Palmer (TAP) formulation, started to garner increasing attention from theorists and practitioners alike. However, despite the rapidly growing popularity of variational approximations in Statistics and Machine Learning, the corresponding theoretical guarantees for these approximations remain largely unexplored. This dissertation addresses this challenge through three main contributions: TAP Approximation in Bayesian Linear Regression: In Chapter 1, a variational representation for the log-normalizing constant of the posterior distribution in Bayesian linear regression is derived in the proportional asymptotic regime, assuming a uniform spherical prior and i.i.d. Gaussian designs. Performance of NMF in Linear Regression: Chapter 2 investigates the NMF approximation in linear regression under proportional asymptotics. It confirms the inaccuracy of NMF for approximating the log-normalizing constant and supports empirical observations of NMF being overconfident. NMF in Generalized Linear Models (GLMs): Chapter 3 identifies conditions under which the NMF approximation is valid in high-dimensional GLMs. Algorithmic insights and probabilistic properties of the high-dimensional posteriors were also investigated.
일반주제명  
Statistics
일반주제명  
Applied mathematics
일반주제명  
Statistical physics
키워드  
Variational inference
키워드  
Thouless-Anderson-Palmer
키워드  
Linear regression
키워드  
Bayesian models
키워드  
Gaussian designs
기타저자  
Harvard University Statistics
기본자료저록  
Dissertations Abstracts International. 85-12B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017160359
■00520250211151004
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382781877
■035    ▼a(MiAaPQ)AAI30994432
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a310
■1001  ▼aQiu,  Jiaze.▼0(orcid)0000-0003-3895-1859
■24510▼aVariational  Inference  in  High-dimensional  Bayesian  Regression  Models
■260    ▼a[Sl]▼bHarvard  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a184  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-12,  Section:  B.
■500    ▼aAdvisor:  Sen,  Subhabrata.
■5021  ▼aThesis  (Ph.D.)--Harvard  University,  2024.
■520    ▼aIn  modern  applications  of  Bayesian  Statistics,  the  posterior  distribution  is  typically  high-dimensional  and  analytically  intractable.  Variational  Inference  (VI)  has  emerged  as  an  attractive  option  to  approximate  these  intractable  distributions,  facilitating  fast,  parallel  computations.  The  simplest  version  of  VI  is  the  Naive  Mean-field  approximation  (NMF),  where  the  distribution  of  interest  is  approximated  by  a  product  distribution.  In  recent  years,  another  strategy  rooted  in  statistical  physics,  the  Thouless-Anderson-Palmer  (TAP)  formulation,  started  to  garner  increasing  attention  from  theorists  and  practitioners  alike.  However,  despite  the  rapidly  growing  popularity  of  variational  approximations  in  Statistics  and  Machine  Learning,  the  corresponding  theoretical  guarantees  for  these  approximations  remain  largely  unexplored.  This  dissertation  addresses  this  challenge  through  three  main  contributions:  TAP  Approximation  in  Bayesian  Linear  Regression:  In  Chapter  1,  a  variational  representation  for  the  log-normalizing  constant  of  the  posterior  distribution  in  Bayesian  linear  regression  is  derived  in  the  proportional  asymptotic  regime,  assuming  a  uniform  spherical  prior  and  i.i.d.  Gaussian  designs.  Performance  of  NMF  in  Linear  Regression:  Chapter  2  investigates  the  NMF  approximation  in  linear  regression  under  proportional  asymptotics.  It  confirms  the  inaccuracy  of  NMF  for  approximating  the  log-normalizing  constant  and  supports  empirical  observations  of  NMF  being  overconfident.  NMF  in  Generalized  Linear  Models  (GLMs):  Chapter  3  identifies  conditions  under  which  the  NMF  approximation  is  valid  in  high-dimensional  GLMs.  Algorithmic  insights  and  probabilistic  properties  of  the  high-dimensional  posteriors  were  also  investigated.
■590    ▼aSchool  code:  0084.
■650  4▼aStatistics
■650  4▼aApplied  mathematics
■650  4▼aStatistical  physics
■653    ▼aVariational  inference
■653    ▼aThouless-Anderson-Palmer
■653    ▼aLinear  regression
■653    ▼aBayesian  models
■653    ▼aGaussian  designs
■690    ▼a0463
■690    ▼a0364
■690    ▼a0217
■71020▼aHarvard  University▼bStatistics.
■7730  ▼tDissertations  Abstracts  International▼g85-12B.
■790    ▼a0084
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17160359▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF13928 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.