서브메뉴
검색
Trustworthy Machine Learning: Privacy-Preserving and Adversarially Robust Optimization Algorithms
Trustworthy Machine Learning: Privacy-Preserving and Adversarially Robust Optimization Algorithms
Detailed Information
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105130
- ISBN
- 9798291553381
- DDC
- 004
- 저자명
- Gao, Changyu.
- 서명/저자
- Trustworthy Machine Learning: Privacy-Preserving and Adversarially Robust Optimization Algorithms
- 발행사항
- [Sl] : The University of Wisconsin - Madison, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 232 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-02, Section: B.
- 주기사항
- Advisor: Wright, Stephen.
- 학위논문주기
- Thesis (Ph.D.)--The University of Wisconsin - Madison, 2025.
- 초록/해제
- 요약This thesis investigates the development of trustworthy machine learning systems by focusing on two critical areas: privacy and robustness. We introduce and analyze novel optimization algorithms designed to perform effectively under the rigorous constraints of differential privacy and in the presence of adversarial data perturbations. The central aim is to design algorithms that are not only theoretically sound but also practically efficient, addressing fundamental trade-offs between privacy, robustness, and computational performance in modern machine learning.Key contributions of this work include the following: the development of a practical and efficient framework for differentially private nonconvex optimization (Chapter 2) that finds approximate second-order solutions. In the distributed setting, we present novel algorithms for federated learning (Chapter 3) that achieve optimal excess risk bounds with superior communication efficiency for heterogeneous data, resolving a previously open problem. To address adversarial data corruption, in Chapter 4, we develop a novel algorithm for robust stochastic convex optimization under the strong contamination model that achieves minimax-optimal excess risk. The work also provides a broader perspective on the landscape of private learning by summarizing key sample complexity results and charting future research directions (Chapter 5). We provide partial results to these open problems. Notably we present the first algorithm achieving both differential privacy and adversarial robustness simultaneously for stochastic convex optimization.In summary, this dissertation advances the state-of-the-art by providing new algorithms with strong theoretical guarantees and practical advantages for private and robust machine learning. The findings presented offer a deeper understanding of the fundamental trade-offs between privacy, robustness, and computational efficiency, paving the way for more reliable and secure machine learning systems.
- 일반주제명
- Computer science
- 일반주제명
- Computer engineering
- 키워드
- Nonsmooth loss
- 기타저자
- The University of Wisconsin - Madison Industrial Engineering
- 기본자료저록
- Dissertations Abstracts International. 87-02B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017359513
■00520260202105130
■006m o d
■007cr#unu||||||||
■020 ▼a9798291553381
■035 ▼a(MiAaPQ)AAI32239182
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aGao, Changyu.
■24510▼aTrustworthy Machine Learning: Privacy-Preserving and Adversarially Robust Optimization Algorithms
■260 ▼a[Sl]▼bThe University of Wisconsin - Madison▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a232 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-02, Section: B.
■500 ▼aAdvisor: Wright, Stephen.
■5021 ▼aThesis (Ph.D.)--The University of Wisconsin - Madison, 2025.
■520 ▼aThis thesis investigates the development of trustworthy machine learning systems by focusing on two critical areas: privacy and robustness. We introduce and analyze novel optimization algorithms designed to perform effectively under the rigorous constraints of differential privacy and in the presence of adversarial data perturbations. The central aim is to design algorithms that are not only theoretically sound but also practically efficient, addressing fundamental trade-offs between privacy, robustness, and computational performance in modern machine learning.Key contributions of this work include the following: the development of a practical and efficient framework for differentially private nonconvex optimization (Chapter 2) that finds approximate second-order solutions. In the distributed setting, we present novel algorithms for federated learning (Chapter 3) that achieve optimal excess risk bounds with superior communication efficiency for heterogeneous data, resolving a previously open problem. To address adversarial data corruption, in Chapter 4, we develop a novel algorithm for robust stochastic convex optimization under the strong contamination model that achieves minimax-optimal excess risk. The work also provides a broader perspective on the landscape of private learning by summarizing key sample complexity results and charting future research directions (Chapter 5). We provide partial results to these open problems. Notably we present the first algorithm achieving both differential privacy and adversarial robustness simultaneously for stochastic convex optimization.In summary, this dissertation advances the state-of-the-art by providing new algorithms with strong theoretical guarantees and practical advantages for private and robust machine learning. The findings presented offer a deeper understanding of the fundamental trade-offs between privacy, robustness, and computational efficiency, paving the way for more reliable and secure machine learning systems.
■590 ▼aSchool code: 0262.
■650 4▼aComputer science
■650 4▼aComputer engineering
■653 ▼aAdversarial robustness
■653 ▼aDifferential privacy
■653 ▼aMathematical optimization
■653 ▼aNonsmooth loss
■653 ▼aTrustworthy machine learning
■690 ▼a0796
■690 ▼a0984
■690 ▼a0464
■71020▼aThe University of Wisconsin - Madison▼bIndustrial Engineering.
■7730 ▼tDissertations Abstracts International▼g87-02B.
■790 ▼a0262
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359513▼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.


