본문

서브메뉴

Interactive Machine Learning With Heterogeneous Data
Interactive Machine Learning With Heterogeneous Data
Interactive Machine Learning With Heterogeneous Data

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211151012
ISBN  
9798382303888
DDC  
004
저자명  
Wang, Zhi.
서명/저자  
Interactive Machine Learning With Heterogeneous Data
발행사항  
[Sl] : University of California, San Diego, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
362 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-10, Section: A.
주기사항  
Advisor: Chaudhuri, Kamalika.
학위논문주기  
Thesis (Ph.D.)--University of California, San Diego, 2024.
초록/해제  
요약In interactive machine learning, learners utilize data collected from interacting with the environment or with humans to better achieve their goals. Real-world applications often involve heterogeneous data sources, such as a large pool of human users with diverse interests or preferences, or non-stationary environments with distribution shifts. In this dissertation, we investigate interactive machine learning in the presence of heterogeneous data. In particular, we study when and how provably efficient learning can be achieved when the heterogeneous data exhibit structure.In the first part, we study transfer learning in sequential decision-making. We consider a setting where learners are deployed to perform tasks in similar yet nonidentical multi-armed bandit environments. We study when and how knowledge acquired from one environment can be robustly transferred to others so as to improve the collective performance of the learners. We present two provably efficient algorithms that properly manage data collected across heterogeneous environments: one uses upper confidence bounds and the other is based on Thompson sampling. We then generalize the setting and certain results to multi-task reinforcement learning in tabular Markov decision processes.In the second part, we study metric learning from crowdsourced preference comparisons. In particular, we consider the ideal point model in preference learning, where a user prefers an item over another if it is closer to their latent ideal point. While users may have individual preferences and distinct ideal points, our goal is to learn a common Mahalanobis distance, which provides a more accurate measure of "closeness" that aligns with human values, perception and preferences. We study when and how such a metric can be learned if we can query each user a few times, asking questions in the form of "Do you prefer item A or B?".
일반주제명  
Computer science
일반주제명  
Information science
키워드  
Machine learning
키워드  
Decision-making
키워드  
Heterogeneous data sources
키워드  
Efficient learning
기타저자  
University of California, San Diego Computer Science and Engineering
기본자료저록  
Dissertations Abstracts International. 85-10A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017160404
■00520250211151012
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382303888
■035    ▼a(MiAaPQ)AAI30995604
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aWang,  Zhi.
■24510▼aInteractive  Machine  Learning  With  Heterogeneous  Data
■260    ▼a[Sl]▼bUniversity  of  California,  San  Diego▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a362  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-10,  Section:  A.
■500    ▼aAdvisor:  Chaudhuri,  Kamalika.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  San  Diego,  2024.
■520    ▼aIn  interactive  machine  learning,  learners  utilize  data  collected  from  interacting  with  the  environment  or  with  humans  to  better  achieve  their  goals.  Real-world  applications  often  involve  heterogeneous  data  sources,  such  as  a  large  pool  of  human  users  with  diverse  interests  or  preferences,  or  non-stationary  environments  with  distribution  shifts.  In  this  dissertation,  we  investigate  interactive  machine  learning  in  the  presence  of  heterogeneous  data.  In  particular,  we  study  when  and  how  provably  efficient  learning  can  be  achieved  when  the  heterogeneous  data  exhibit  structure.In  the  first  part,  we  study  transfer  learning  in  sequential  decision-making.  We  consider  a  setting  where  learners  are  deployed  to  perform  tasks  in  similar  yet  nonidentical multi-armed  bandit  environments.  We  study  when  and  how  knowledge  acquired  from  one  environment  can  be  robustly  transferred  to  others  so  as  to  improve  the  collective  performance  of  the  learners.  We  present  two  provably  efficient  algorithms  that  properly  manage  data  collected  across  heterogeneous  environments:  one  uses  upper  confidence  bounds  and  the  other  is  based  on  Thompson  sampling.  We  then  generalize  the  setting  and  certain  results  to  multi-task  reinforcement  learning  in  tabular  Markov  decision  processes.In  the  second  part,  we  study  metric  learning  from  crowdsourced  preference  comparisons.  In  particular,  we  consider  the  ideal  point  model  in  preference  learning,  where  a  user  prefers  an  item  over  another  if  it  is  closer  to  their  latent  ideal  point.  While  users  may  have  individual  preferences  and  distinct  ideal  points,  our  goal  is  to  learn  a  common  Mahalanobis  distance,  which  provides  a  more  accurate  measure  of  "closeness"  that  aligns  with  human  values,  perception  and  preferences.  We  study  when  and  how  such  a  metric  can  be  learned  if  we  can  query  each  user  a  few  times,  asking  questions  in  the  form  of  "Do  you  prefer  item  A  or  B?".
■590    ▼aSchool  code:  0033.
■650  4▼aComputer  science
■650  4▼aInformation  science
■653    ▼aMachine  learning
■653    ▼aDecision-making
■653    ▼aHeterogeneous  data  sources
■653    ▼aEfficient  learning
■690    ▼a0984
■690    ▼a0800
■690    ▼a0723
■71020▼aUniversity  of  California,  San  Diego▼bComputer  Science  and  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-10A.
■790    ▼a0033
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17160404▼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
    TF14133 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.