서브메뉴
검색
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
- 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.


