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