본문

서브메뉴

Algorithm Dynamics in Modern Statistical Learning: Asymptotics, Universality, and Implicit Regularization
Algorithm Dynamics in Modern Statistical Learning: Asymptotics, Universality, and Implicit...
Algorithm Dynamics in Modern Statistical Learning: Asymptotics, Universality, and Implicit Regularization

Detailed Information

Material Type  
 단행본
 
0017160537
Date and Time of Latest Transaction  
20250211151036
ISBN  
9798383482179
DDC  
310
Author  
Wang, Tianhao.
Title/Author  
Algorithm Dynamics in Modern Statistical Learning: Asymptotics, Universality, and Implicit Regularization
Publish Info  
[Sl] : Yale University, 2024
Publish Info  
Ann Arbor : ProQuest Dissertations & Theses, 2024
Material Info  
349 p
General Note  
Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
General Note  
Advisor: Fan, Zhou.
학위논문주기  
Thesis (Ph.D.)--Yale University, 2024.
Abstracts/Etc  
요약Understanding the dynamics of algorithms is crucial for characterizing the behavior of trained models in modern statistical learning. This thesis presents a few recent results on theoretical analyses of the dynamics of two classes of algorithms: Approximate Message Passing (AMP) algorithms and Stochastic Gradient Descent (SGD). For AMP algorithms, the focus is to derive the precise asymptotic distributional characterization of the iterates, known as the ``state evolution'' which summarizes the dynamics of AMP iterates, and to understand the universality of such characterization with respect to the underlying data distribution. For SGD, the goal is to perform trajectory analysis to understand its implicit regularization, a key property believed to be essential for the generalization of modern deep learning models. The results presented here provide unified frameworks for analyzing and understanding the dynamics of these algorithms, and can be potentially extended to other algorithms.
Subject Added Entry-Topical Term  
Statistics
Index Term-Uncontrolled  
Approximate message passing
Index Term-Uncontrolled  
Implicit regularization
Index Term-Uncontrolled  
Stochastic gradient descent
Index Term-Uncontrolled  
Universality
Added Entry-Corporate Name  
Yale University Statistics and Data Science
Host Item Entry  
Dissertations Abstracts International. 86-01B.
Electronic Location and Access  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017160537
■00520250211151036
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798383482179
■035    ▼a(MiAaPQ)AAI30997623
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a310
■1001  ▼aWang,  Tianhao.
■24510▼aAlgorithm  Dynamics  in  Modern  Statistical  Learning:  Asymptotics,  Universality,  and  Implicit  Regularization
■260    ▼a[Sl]▼bYale  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a349  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-01,  Section:  B.
■500    ▼aAdvisor:  Fan,  Zhou.
■5021  ▼aThesis  (Ph.D.)--Yale  University,  2024.
■520    ▼aUnderstanding  the  dynamics  of  algorithms  is  crucial  for  characterizing  the  behavior  of  trained  models  in  modern  statistical  learning.  This  thesis  presents  a  few  recent  results  on  theoretical  analyses  of  the  dynamics  of  two  classes  of  algorithms:  Approximate  Message  Passing  (AMP)  algorithms  and  Stochastic  Gradient  Descent  (SGD).  For  AMP  algorithms,  the  focus  is  to  derive  the  precise  asymptotic  distributional  characterization  of  the  iterates,  known  as  the  ``state  evolution''  which  summarizes  the  dynamics  of  AMP  iterates,  and  to  understand  the  universality  of  such  characterization  with  respect  to  the  underlying  data  distribution.  For  SGD,  the  goal  is  to  perform  trajectory  analysis  to  understand  its  implicit  regularization,  a  key  property  believed  to  be  essential  for  the  generalization  of  modern  deep  learning  models.  The  results  presented  here  provide  unified  frameworks  for  analyzing  and  understanding  the  dynamics  of  these  algorithms,  and  can  be  potentially  extended  to  other  algorithms.
■590    ▼aSchool  code:  0265.
■650  4▼aStatistics
■653    ▼aApproximate  message  passing
■653    ▼aImplicit  regularization
■653    ▼aStochastic  gradient  descent
■653    ▼aUniversality
■690    ▼a0463
■71020▼aYale  University▼bStatistics  and  Data  Science.
■7730  ▼tDissertations  Abstracts  International▼g86-01B.
■790    ▼a0265
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17160537▼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

    Detail Info.

    • Reservation
    • Not Exist
    • My Folder
    • First Request
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    Material
    Reg No. Call No. Location Status Lend Info
    TF10017 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Reservations are available in the borrowing book. To make reservations, Please click the reservation button

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.