서브메뉴
검색
Distribution-Free Uncertainty Quantification for Deep Learning
Distribution-Free Uncertainty Quantification for Deep Learning
Detailed Information
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105705
- ISBN
- 9798263308346
- DDC
- 310
- 저자명
- Lin, Zhen.
- 서명/저자
- Distribution-Free Uncertainty Quantification for Deep Learning
- 발행사항
- [Sl] : University of Illinois at Urbana-Champaign, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 248 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-05, Section: A.
- 주기사항
- Advisor: Sun, Jimeng.
- 학위논문주기
- Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2024.
- 초록/해제
- 요약The integration of sophisticated deep learning models into critical domains, such as healthcare, autonomous vehicles, and the legal system, is increasingly becoming a trend. These models offer significant potential for enhancing outcomes efficiently, but their adoption raises crucial challenges related to model confidence, uncertainty communication, and risk management. Uncertainty Quantification (UQ) is a key framework that addresses these issues by providing a systematic way to assess and act on the reliability of model predictions.This thesis focuses on distribution-free UQ methods, which require minimal assumptions about the data distribution and model specifics, making them highly applicable across various deep learning applications. We first investigate the problem of full calibration for deep learning classifiers, aiming to address the over-confidence or under-confidence typically observed in such classifiers. Then, we discuss methods to convert a model's output into actionable uncertainty information, expressed as prediction intervals and prediction sets. In particular, we focus on the construction of prediction intervals and sets with rigorous coverage or risk control guarantees, typically provided by conformal prediction tools. Finally, we explore the problem of UQ for natural language generation (NLG), for which we apply a graph-based approach using the similarity graph of multiple sampled responses. Through exploring model calibration, risk-controlling prediction sets, conformal prediction intervals, and UQ for NLG, this thesis aims to advance the understanding and implementation of UQ in high-stakes decision-making environments.
- 일반주제명
- Statistics
- 일반주제명
- Computer science
- 일반주제명
- Linguistics
- 키워드
- Deep learning
- 키워드
- Machine learning
- 키워드
- Prediction sets
- 키워드
- Neural networks
- 기타저자
- University of Illinois at Urbana-Champaign Computer Science
- 기본자료저록
- Dissertations Abstracts International. 87-05A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2024 us c eng d■001000017361096
■00520260202105705
■006m o d
■007cr#unu||||||||
■020 ▼a9798263308346
■035 ▼a(MiAaPQ)AAI32409923
■035 ▼a(MiAaPQ)124231
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a310
■1001 ▼aLin, Zhen.
■24510▼aDistribution-Free Uncertainty Quantification for Deep Learning
■260 ▼a[Sl]▼bUniversity of Illinois at Urbana-Champaign▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a248 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-05, Section: A.
■500 ▼aAdvisor: Sun, Jimeng.
■5021 ▼aThesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2024.
■520 ▼aThe integration of sophisticated deep learning models into critical domains, such as healthcare, autonomous vehicles, and the legal system, is increasingly becoming a trend. These models offer significant potential for enhancing outcomes efficiently, but their adoption raises crucial challenges related to model confidence, uncertainty communication, and risk management. Uncertainty Quantification (UQ) is a key framework that addresses these issues by providing a systematic way to assess and act on the reliability of model predictions.This thesis focuses on distribution-free UQ methods, which require minimal assumptions about the data distribution and model specifics, making them highly applicable across various deep learning applications. We first investigate the problem of full calibration for deep learning classifiers, aiming to address the over-confidence or under-confidence typically observed in such classifiers. Then, we discuss methods to convert a model's output into actionable uncertainty information, expressed as prediction intervals and prediction sets. In particular, we focus on the construction of prediction intervals and sets with rigorous coverage or risk control guarantees, typically provided by conformal prediction tools. Finally, we explore the problem of UQ for natural language generation (NLG), for which we apply a graph-based approach using the similarity graph of multiple sampled responses. Through exploring model calibration, risk-controlling prediction sets, conformal prediction intervals, and UQ for NLG, this thesis aims to advance the understanding and implementation of UQ in high-stakes decision-making environments.
■590 ▼aSchool code: 0090.
■650 4▼aStatistics
■650 4▼aComputer science
■650 4▼aLinguistics
■653 ▼aUncertainty Quantification
■653 ▼aDeep learning
■653 ▼aMachine learning
■653 ▼aConformal prediction
■653 ▼aPrediction sets
■653 ▼aNeural networks
■653 ▼aHealthcare applications
■690 ▼a0984
■690 ▼a0463
■690 ▼a0800
■690 ▼a0290
■71020▼aUniversity of Illinois at Urbana-Champaign▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g87-05A.
■790 ▼a0090
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17361096▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
Preview
Export
ChatGPT Discussion
AI Recommended Related Books
Подробнее информация.
- Бронирование
- не существует
- моя папка
- Первый запрос зрения
- Non-Book Loan Application
- Nighttime Book Loan Application
Available after logging in.


