본문

서브메뉴

Principled Algorithms for Domain Adaptation and Generalization- [electronic resource]
Principled Algorithms for Domain Adaptation and Generalization- [electronic resource]

상세정보

자료유형  
 학위논문
Control Number  
0016934563
International Standard Book Number  
9798380485050
Dewey Decimal Classification Number  
004
Main Entry-Personal Name  
Chen, Yining.
Publication, Distribution, etc. (Imprint  
[S.l.] : Stanford University., 2023
Publication, Distribution, etc. (Imprint  
Ann Arbor : ProQuest Dissertations & Theses, 2023
Physical Description  
1 online resource(229 p.)
General Note  
Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
General Note  
Advisor: Ma, Tengyu.
Dissertation Note  
Thesis (Ph.D.)--Stanford University, 2023.
Restrictions on Access Note  
This item must not be sold to any third party vendors.
Summary, Etc.  
요약Machine learning models are increasingly applied to datasets different from the training datasets. The performance of models often degrades when tested on unseen scenarios. Empirically, many algorithms have been used for domain adaptation and generalization, but few methods have been able to surpass empirical risk minimization consistently on common benchmarks. Theoretically, traditional learning theory offers limited insights for distributional shift problems. The main goal of this thesis is to bridge the gap between the theory and practice for domain shift problems, and to develop principled algorithms that have better robustness guarantees.We study three domain shift problems with increased supervised from the target domain. We first study domain generalization where no target data is available during training. We show that feature-matching algorithms generalize better when the distinguishing property of the signal feature is indeed conditional distributional invariance. Next, we study domain adaptation where unlabeled target data is available. We show that self-training helps when the target is more diverse than the source. Lastly, we study active online learning under domain shift. We show that uncertainty sampling leads to better query-regret tradeoff when there is hidden domain structure. In all three problems, the synergy of explicit bias from the algorithm and implicit bias from the domain shift structure contributes to successful transfer between domains.
Subject Added Entry-Topical Term  
Active learning.
Subject Added Entry-Topical Term  
Computer science.
Added Entry-Corporate Name  
Stanford University.
Host Item Entry  
Dissertations Abstracts International. 85-04B.
Host Item Entry  
Dissertation Abstract International
Electronic Location and Access  
로그인을 한후 보실 수 있는 자료입니다.
Control Number  
joongbu:639850

MARC

 008240219s2023        ulk                      00        kor
■001000016934563
■00520240214101626
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798380485050
■035    ▼a(MiAaPQ)AAI30615214
■035    ▼a(MiAaPQ)STANFORDdm107nr6713
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aChen,  Yining.
■24510▼aPrincipled  Algorithms  for  Domain  Adaptation  and  Generalization▼h[electronic  resource]
■260    ▼a[S.l.]▼bStanford  University.  ▼c2023
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2023
■300    ▼a1  online  resource(229  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-04,  Section:  B.
■500    ▼aAdvisor:  Ma,  Tengyu.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aMachine  learning  models  are  increasingly  applied  to  datasets  different  from  the  training  datasets.  The  performance  of  models  often  degrades  when  tested  on  unseen  scenarios.  Empirically,  many  algorithms  have  been  used  for  domain  adaptation  and  generalization,  but  few  methods  have  been  able  to  surpass  empirical  risk  minimization  consistently  on  common  benchmarks.  Theoretically,  traditional  learning  theory  offers  limited  insights  for  distributional  shift  problems.  The  main  goal  of  this  thesis  is  to  bridge  the  gap  between  the  theory  and  practice  for  domain  shift  problems,  and  to  develop  principled  algorithms  that  have  better  robustness  guarantees.We  study  three  domain  shift  problems  with  increased  supervised  from  the  target  domain.  We  first  study  domain  generalization  where  no  target  data  is  available  during  training.  We  show  that  feature-matching  algorithms  generalize  better  when  the  distinguishing  property  of  the  signal  feature  is  indeed  conditional  distributional  invariance.  Next,  we  study  domain  adaptation  where  unlabeled  target  data  is  available.  We  show  that  self-training  helps  when  the  target  is  more  diverse  than  the  source.  Lastly,  we  study  active  online  learning  under  domain  shift.  We  show  that  uncertainty  sampling  leads  to  better  query-regret  tradeoff  when  there  is  hidden  domain  structure.  In  all  three  problems,  the  synergy  of  explicit  bias  from  the  algorithm  and  implicit  bias  from  the  domain  shift  structure  contributes  to  successful  transfer  between  domains.
■590    ▼aSchool  code:  0212.
■650  4▼aActive  learning.
■650  4▼aComputer  science.
■690    ▼a0800
■690    ▼a0984
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g85-04B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16934563▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    New Books MORE
    Related books MORE
    최근 3년간 통계입니다.

    Info Détail de la recherche.

    • Réservation
    • 캠퍼스간 도서대출
    • 서가에 없는 책 신고
    • My Folder
    Matériel
    Reg No. Call No. emplacement Status Lend Info
    TQ0025778 T   원문자료 열람가능/출력가능 열람가능/출력가능
    마이폴더 부재도서신고

    * Les réservations sont disponibles dans le livre d'emprunt. Pour faire des réservations, S'il vous plaît cliquer sur le bouton de réservation

    해당 도서를 다른 이용자가 함께 대출한 도서

    Related books

    Related Popular Books

    도서위치