서브메뉴
검색
Reliable and Adaptive Stochastic Optimization in the Face of Messy Data
Reliable and Adaptive Stochastic Optimization in the Face of Messy Data
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151347
- ISBN
- 9798382842257
- DDC
- 510
- 저자명
- Xie, Miaolan.
- 서명/저자
- Reliable and Adaptive Stochastic Optimization in the Face of Messy Data
- 발행사항
- [Sl] : Cornell University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 151 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-12, Section: A.
- 주기사항
- Advisor: Scheinberg, Katya.
- 학위논문주기
- Thesis (Ph.D.)--Cornell University, 2024.
- 초록/해제
- 요약Solving real-world stochastic optimization problems (e.g., in machine learning) presents two key challenges: the messiness of real-world data, which can be noisy, biased, or corrupted due to factors like outliers, distribution shifts, and even adversarial attacks; and the laborious, time-intensive requirement of manually tuning step sizes in many existing algorithms.I study stochastic adaptive optimization algorithms under a simple, common framework. The algorithms in this framework avoid the need for manual step size tuning by adaptively adjusting it in each iteration based on the algorithm's progress. To address the issue of messy data, the framework only assumes access to function-related information through probabilistic oracles, which may be biased and corrupted. This framework is very general, encompassing a wide range of algorithms, and is applicable to multiple problem settings, such as expected loss minimization in machine learning, simulation optimization, and derivative-free optimization. We establish iteration complexity bounds for two algorithms within it - stochastic adaptive step search and stochastic adaptive cubic-regularized Newton method - under reasonable oracle conditions. Additionally, we derive a meta-theorem to bound the sample complexity for any algorithm in the framework.
- 일반주제명
- Mathematics
- 일반주제명
- Computer science
- 일반주제명
- Information science
- 키워드
- Messy data
- 기타저자
- Cornell University Operations Research and Information Engineering
- 기본자료저록
- Dissertations Abstracts International. 85-12A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017161372
■00520250211151347
■006m o d
■007cr#unu||||||||
■020 ▼a9798382842257
■035 ▼a(MiAaPQ)AAI31242760
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a510
■1001 ▼aXie, Miaolan.▼0(orcid)0000-0001-8511-9649
■24510▼aReliable and Adaptive Stochastic Optimization in the Face of Messy Data
■260 ▼a[Sl]▼bCornell University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a151 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-12, Section: A.
■500 ▼aAdvisor: Scheinberg, Katya.
■5021 ▼aThesis (Ph.D.)--Cornell University, 2024.
■520 ▼aSolving real-world stochastic optimization problems (e.g., in machine learning) presents two key challenges: the messiness of real-world data, which can be noisy, biased, or corrupted due to factors like outliers, distribution shifts, and even adversarial attacks; and the laborious, time-intensive requirement of manually tuning step sizes in many existing algorithms.I study stochastic adaptive optimization algorithms under a simple, common framework. The algorithms in this framework avoid the need for manual step size tuning by adaptively adjusting it in each iteration based on the algorithm's progress. To address the issue of messy data, the framework only assumes access to function-related information through probabilistic oracles, which may be biased and corrupted. This framework is very general, encompassing a wide range of algorithms, and is applicable to multiple problem settings, such as expected loss minimization in machine learning, simulation optimization, and derivative-free optimization. We establish iteration complexity bounds for two algorithms within it - stochastic adaptive step search and stochastic adaptive cubic-regularized Newton method - under reasonable oracle conditions. Additionally, we derive a meta-theorem to bound the sample complexity for any algorithm in the framework.
■590 ▼aSchool code: 0058.
■650 4▼aMathematics
■650 4▼aComputer science
■650 4▼aInformation science
■653 ▼aMathematical optimization
■653 ▼aNonlinear optimization
■653 ▼aSimulation optimization
■653 ▼aStochastic optimization
■653 ▼aMessy data
■690 ▼a0796
■690 ▼a0984
■690 ▼a0723
■690 ▼a0405
■71020▼aCornell University▼bOperations Research and Information Engineering.
■7730 ▼tDissertations Abstracts International▼g85-12A.
■790 ▼a0058
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161372▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
