본문

서브메뉴

Data-Efficient Decision-Making- [electronic resource]
Data-Efficient Decision-Making - [electronic resource]
Data-Efficient Decision-Making- [electronic resource]

Detailed Information

자료유형  
 학위논문파일 국외
최종처리일시  
20240214100126
ISBN  
9798379711665
DDC  
310
저자명  
Hu, Yichun.
서명/저자  
Data-Efficient Decision-Making - [electronic resource]
발행사항  
[S.l.]: : Cornell University., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(322 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
주기사항  
Advisor: Kallus, Nathan.
학위논문주기  
Thesis (Ph.D.)--Cornell University, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약This thesis is focused on the development of sample-efficient algorithms for personalized data-driven decision-making. In particular, the dissertation aims to address the following questions in both online (sequential) and offline (batch) settings: (i) What problem structures allow for achieving instance-specific fast regret rates? (ii) How can these problem structures be leveraged to design practical algorithms that achieve fast theoretical rates?Part I of this thesis investigates the above questions from an online perspective. Chapter 2 studies the smooth contextual bandit problem, where we use the smoothness property of the function class to design contextual bandit algorithms that interpolate between two extremes previously studied in isolation: nondifferentiable bandits and parametric-response bandits. Chapter 3 examines the DTR bandit problem, where we develop the first online algorithm with logarithmic regret for dynamic treatment regimes that involve personalized, adaptive, multi-stage treatment plans.Part II of this work delves into fast regret rates for offline problems by leveraging a probabilistic condition that measures the distribution of the reward gap between the optimal and second-optimal decisions, which we term the margin condition. In the case of contextual linear optimization, Chapter 4 shows that the naive plug-in approach actually achieves regret convergence rates that are significantly faster than methods that directly optimize downstream decision performance. In the case of offline reinforcement learning, Chapter 5 presents a finer regret analysis that characterizes the faster-than-square-root regret convergence rate we observe in practice.
일반주제명  
Statistics.
일반주제명  
Computer science.
키워드  
Data
키워드  
Decision-making
키워드  
Algorithms
키워드  
Fast regret rates
키워드  
Contextual bandit algorithms
기타저자  
Cornell University Operations Research and Information Engineering
기본자료저록  
Dissertations Abstracts International. 84-12B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2023      us  |||||||||||||||c||eng  d
■001000016931842
■00520240214100126
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798379711665
■035    ▼a(MiAaPQ)AAI30425306
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a310
■1001  ▼aHu,  Yichun.▼0(orcid)0000-0002-5826-9665
■24510▼aData-Efficient  Decision-Making▼h[electronic  resource]
■260    ▼a[S.l.]:▼bCornell  University.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(322  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  84-12,  Section:  B.
■500    ▼aAdvisor:  Kallus,  Nathan.
■5021  ▼aThesis  (Ph.D.)--Cornell  University,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aThis  thesis  is  focused  on  the  development  of  sample-efficient  algorithms  for  personalized  data-driven  decision-making.  In  particular,  the  dissertation  aims  to  address  the  following  questions  in  both  online  (sequential)  and  offline  (batch)  settings:  (i)  What  problem  structures  allow  for  achieving  instance-specific  fast  regret  rates?  (ii)  How  can  these  problem  structures  be  leveraged  to  design  practical  algorithms  that  achieve  fast  theoretical  rates?Part  I  of  this  thesis  investigates  the  above  questions  from  an  online  perspective.  Chapter  2  studies  the  smooth  contextual  bandit  problem,  where  we  use  the  smoothness  property  of  the  function  class  to  design  contextual  bandit  algorithms  that  interpolate  between  two  extremes  previously  studied  in  isolation:  nondifferentiable  bandits  and  parametric-response  bandits.  Chapter  3  examines  the  DTR  bandit  problem,  where  we  develop  the  first  online  algorithm  with  logarithmic  regret  for  dynamic  treatment  regimes  that  involve  personalized,  adaptive,  multi-stage  treatment  plans.Part  II  of  this  work  delves  into  fast  regret  rates  for  offline  problems  by  leveraging  a  probabilistic  condition  that  measures  the  distribution  of  the  reward  gap  between  the  optimal  and  second-optimal  decisions,  which  we  term  the  margin  condition.  In  the  case  of  contextual  linear  optimization,  Chapter  4  shows  that  the  naive  plug-in  approach  actually  achieves  regret  convergence  rates  that  are  significantly  faster  than  methods  that  directly  optimize  downstream  decision  performance.  In  the  case  of  offline  reinforcement  learning,  Chapter  5  presents  a  finer  regret  analysis  that  characterizes  the  faster-than-square-root  regret  convergence  rate  we  observe  in  practice.
■590    ▼aSchool  code:  0058.
■650  4▼aStatistics.
■650  4▼aComputer  science.
■653    ▼aData
■653    ▼aDecision-making
■653    ▼aAlgorithms
■653    ▼aFast  regret  rates
■653    ▼aContextual  bandit  algorithms
■690    ▼a0796
■690    ▼a0463
■690    ▼a0984
■71020▼aCornell  University▼bOperations  Research  and  Information  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g84-12B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0058
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16931842▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


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

    detalle info

    • Reserva
    • No existe
    • Mi carpeta
    • Primera solicitud
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    Material
    número de libro número de llamada Ubicación estado Prestar info
    TF06051 전자도서 My Folder 부재도서신고 비도서대출신청

    * Las reservas están disponibles en el libro de préstamos. Para hacer reservaciones, haga clic en el botón de reserva

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.