본문

서브메뉴

Distributional Robustness and Machine Learning Methods for Stochastic Decision-Making
Distributional Robustness and Machine Learning Methods for Stochastic Decision-Making
Distributional Robustness and Machine Learning Methods for Stochastic Decision-Making

Detailed Information

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  
Distributional robustness
키워드  
Machine learning
키워드  
Stochastic decision-making
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.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF13781 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.