서브메뉴
검색
Distributional Robustness and Machine Learning Methods for Stochastic Decision-Making
Distributional Robustness and Machine Learning Methods for Stochastic Decision-Making
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211153028
- ISBN
- 9798342747066
- DDC
- 519.5
- 저자명
- Zeng, Yibo.
- 서명/저자
- Distributional Robustness and Machine Learning Methods for Stochastic Decision-Making
- 발행사항
- [Sl] : Columbia University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 224 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
- 주기사항
- Advisor: Lam, Henry;namkoong, Hongseok.
- 학위논문주기
- Thesis (Ph.D.)--Columbia University, 2024.
- 초록/해제
- 요약Recently, data-driven methods are increasingly shaping decision-making across domains such as classification, prediction, optimization, and resource allocation. While machine learning advancements have been pivotal, current models can be insufficient to handle unseen uncertainties from future data or new application domains, leading to unreliable decisions and performance risks. This thesis explores how distributionally robust methods can be combined with modern machine learning techniques to ensure more reliable decision-making. We develop new theoretical results and achieve state-of-the-art empirical results in three areas: generalization bounds in machine learning, queue scheduling with prediction errors, and tabular classification under Y|X shifts.The work is organized into three chapters. In Chapter 2, we derive novel generalization bounds for distributionally robust optimization (DRO). Our analysis implies generalization bounds whose dependence on the hypothesis class appears the minimal possible: The bound depends solely on the true loss function, independent of any other candidates in the hypothesis class. To our best knowledge, it is the first generalization bound of this type in the literature. Chapter 3 investigates optimal scheduling in service systems with prediction errors. We develop a near-optimal index-based policy that incorporates predicted class information. Our results guide model selection with a focus on downstream queueing performance and offer insights into designing queueing systems with AI-based triage. In Chapter 4, we study tabular data classification under \uD835\uDC4C|X shift. We not only build a large-scale testbed, but also demonstrate that large language model (LLM) embeddings significantly improve classification performance, even with few labeled samples from the target domain.
- 키워드
- Machine learning
- 기타저자
- Columbia University Operations Research
- 기본자료저록
- Dissertations Abstracts International. 86-05B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017164660
■00520250211153028
■006m o d
■007cr#unu||||||||
■020 ▼a9798342747066
■035 ▼a(MiAaPQ)AAI31634535
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a519.5
■1001 ▼aZeng, Yibo.
■24510▼aDistributional Robustness and Machine Learning Methods for Stochastic Decision-Making
■260 ▼a[Sl]▼bColumbia University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a224 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-05, Section: B.
■500 ▼aAdvisor: Lam, Henry;namkoong, Hongseok.
■5021 ▼aThesis (Ph.D.)--Columbia University, 2024.
■520 ▼aRecently, data-driven methods are increasingly shaping decision-making across domains such as classification, prediction, optimization, and resource allocation. While machine learning advancements have been pivotal, current models can be insufficient to handle unseen uncertainties from future data or new application domains, leading to unreliable decisions and performance risks. This thesis explores how distributionally robust methods can be combined with modern machine learning techniques to ensure more reliable decision-making. We develop new theoretical results and achieve state-of-the-art empirical results in three areas: generalization bounds in machine learning, queue scheduling with prediction errors, and tabular classification under Y|X shifts.The work is organized into three chapters. In Chapter 2, we derive novel generalization bounds for distributionally robust optimization (DRO). Our analysis implies generalization bounds whose dependence on the hypothesis class appears the minimal possible: The bound depends solely on the true loss function, independent of any other candidates in the hypothesis class. To our best knowledge, it is the first generalization bound of this type in the literature. Chapter 3 investigates optimal scheduling in service systems with prediction errors. We develop a near-optimal index-based policy that incorporates predicted class information. Our results guide model selection with a focus on downstream queueing performance and offer insights into designing queueing systems with AI-based triage. In Chapter 4, we study tabular data classification under \uD835\uDC4C|X shift. We not only build a large-scale testbed, but also demonstrate that large language model (LLM) embeddings significantly improve classification performance, even with few labeled samples from the target domain.
■590 ▼aSchool code: 0054.
■653 ▼aDistributional robustness
■653 ▼aMachine learning
■653 ▼aStochastic decision-making
■690 ▼a0796
■690 ▼a0800
■71020▼aColumbia University▼bOperations Research.
■7730 ▼tDissertations Abstracts International▼g86-05B.
■790 ▼a0054
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164660▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


