서브메뉴
검색
Information-Theoretic Foundations for Machine Learning
Information-Theoretic Foundations for Machine Learning
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202104850
- ISBN
- 9798288817090
- DDC
- 519.2
- 저자명
- Jeon, Hong Jun.
- 서명/저자
- Information-Theoretic Foundations for Machine Learning
- 발행사항
- [Sl] : Stanford University, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 120 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
- 주기사항
- Advisor: Sadigh, Dorsa;Van Roy, Benjamin.
- 학위논문주기
- Thesis (Ph.D.)--Stanford University, 2025.
- 초록/해제
- 요약The progress of machine learning over the past decade is undeniable. In retrospect, it is both remarkable and unsettling that this progress was achievable with little to no rigorous theory to guide experimentation. Despite this fact, practitioners have been able to guide their future experimentation via observations from previous large-scale empirical investigations. However, alluding to Plato's Allegory of the cave, it is likely that the observations which form the field's notion of reality are but shadows representing fragments of that reality. In this work, we propose a theoretical framework which attempts to answer what exists outside of the cave. To the theorist, we provide a framework which is mathematically rigorous and leaves open many interesting ideas for future exploration. To the practitioner, we provide a framework whose results are simple, and provide intuition to guide future investigations across a wide range of learning paradigms. Concretely, we provide a theoretical framework rooted in Bayesian statistics and Shannon's information theory which is general enough to unify the analysis of many phenomena in machine learning. Our framework characterizes the performance of an optimal Bayesian learner as it learns from a stream of experience. Unlike existing analyses that weaken with increasing data complexity, our theoretical tools provide accurate insights across diverse machine learning settings. Throughout this work, we derive theoretical results and demonstrate their generality by applying them to derive insights specific to multiple settings. These settings range from learning from data which is independently and identically distributed under an unknown distribution, to data which is sequential, to data which exhibits hierarchical structure amenable to meta-learning, and finally to data which is not fully explainable under the learner's beliefs (misspecification). These results are particularly relevant as we strive to understand and overcome increasingly difficult machine learning challenges in this endlessly complex world.
- 일반주제명
- Probability
- 일반주제명
- Deep learning
- 일반주제명
- Information theory
- 일반주제명
- Neural networks
- 일반주제명
- Statistics
- 일반주제명
- Computer science
- 키워드
- Machine learning
- 키워드
- Meta-learning
- 기타저자
- Stanford University.
- 기본자료저록
- Dissertations Abstracts International. 87-01B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017359214
■00520260202104850
■006m o d
■007cr#unu||||||||
■020 ▼a9798288817090
■035 ▼a(MiAaPQ)AAI32200951
■035 ▼a(MiAaPQ)Stanfordgx002mv2026
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a519.2
■1001 ▼aJeon, Hong Jun.
■24510▼aInformation-Theoretic Foundations for Machine Learning
■260 ▼a[Sl]▼bStanford University▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a120 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-01, Section: B.
■500 ▼aAdvisor: Sadigh, Dorsa;Van Roy, Benjamin.
■5021 ▼aThesis (Ph.D.)--Stanford University, 2025.
■520 ▼aThe progress of machine learning over the past decade is undeniable. In retrospect, it is both remarkable and unsettling that this progress was achievable with little to no rigorous theory to guide experimentation. Despite this fact, practitioners have been able to guide their future experimentation via observations from previous large-scale empirical investigations. However, alluding to Plato's Allegory of the cave, it is likely that the observations which form the field's notion of reality are but shadows representing fragments of that reality. In this work, we propose a theoretical framework which attempts to answer what exists outside of the cave. To the theorist, we provide a framework which is mathematically rigorous and leaves open many interesting ideas for future exploration. To the practitioner, we provide a framework whose results are simple, and provide intuition to guide future investigations across a wide range of learning paradigms. Concretely, we provide a theoretical framework rooted in Bayesian statistics and Shannon's information theory which is general enough to unify the analysis of many phenomena in machine learning. Our framework characterizes the performance of an optimal Bayesian learner as it learns from a stream of experience. Unlike existing analyses that weaken with increasing data complexity, our theoretical tools provide accurate insights across diverse machine learning settings. Throughout this work, we derive theoretical results and demonstrate their generality by applying them to derive insights specific to multiple settings. These settings range from learning from data which is independently and identically distributed under an unknown distribution, to data which is sequential, to data which exhibits hierarchical structure amenable to meta-learning, and finally to data which is not fully explainable under the learner's beliefs (misspecification). These results are particularly relevant as we strive to understand and overcome increasingly difficult machine learning challenges in this endlessly complex world.
■590 ▼aSchool code: 0212.
■650 4▼aProbability
■650 4▼aDeep learning
■650 4▼aInformation theory
■650 4▼aNeural networks
■650 4▼aStatistics
■650 4▼aComputer science
■653 ▼aMachine learning
■653 ▼aBayesian statistics
■653 ▼aMeta-learning
■690 ▼a0800
■690 ▼a0463
■690 ▼a0984
■71020▼aStanford University.
■7730 ▼tDissertations Abstracts International▼g87-01B.
■790 ▼a0212
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359214▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


