본문

Estimation and Optimization of Information Measures with Applications to Fairness and Differential Privacy- [electronic resource]
Estimation and Optimization of Information Measures with Applications to Fairness and Diff...
내용보기
Estimation and Optimization of Information Measures with Applications to Fairness and Differential Privacy- [electronic resource]
자료유형  
 학위논문파일 국외
최종처리일시  
20240214100500
ISBN  
9798379604790
DDC  
519
저자명  
Alghamdi, Wael Mohammed A.
서명/저자  
Estimation and Optimization of Information Measures with Applications to Fairness and Differential Privacy - [electronic resource]
발행사항  
[S.l.]: : Harvard University., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(373 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 84-12, Section: A.
주기사항  
Advisor: Calmon, Flavio.
학위논문주기  
Thesis (Ph.D.)--Harvard University, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약My dissertation solves three theoretical problems on optimizing and estimating information measures, and it also builds on this theory to introduce novel practical algorithms for: 1) Optimal mechanism design for differential privacy (DP); 2) Optimal group-fair enhancement in machine learning; and 3) Estimation of information measures from data using sample moments. Information measures (in particular, f-divergences) provide a rigorous way to tackle several real-world problems. Examples include: 1) Quantifying the degree of privacy afforded by data releasing mechanisms---using the hockey-stick divergence; 2) Correcting machine learning (ML) trained classifiers for group-fairness---via optimizing cross-entropy; and 3) Detecting new dependencies between pairs of natural phenomena---via estimating mutual information from data. Herein, we put forth mathematically grounded approaches for the above three practical problems. In the first third of the dissertation, we design optimal DP mechanisms in the large-composition regime, and we also derive a fast and accurate DP accountant for the large-composition regime via the method of steepest descent from mathematical physics. We prove that the privacy parameter is equivalent to a KL-divergence term, then we provide solutions to the ensuing minmax KL-divergence problem. In the second third of the dissertation, we generalize the ubiquitous concept of information projection to the case of conditional distributions---which we term model projection. We derive explicit formulas for model projection, as well as a parallelizable algorithm to compute it efficiently and at scale. We instantiate our model projection theory to the domain of group-fair ML, thereby obtaining an optimal multi-class fairness enhancement method that runs in the order of seconds on datasets of size more than 1 million samples. In the last third of the dissertation, we derive the functional form of the relationship between information measures and the underlying moments. Plugging in the sample moments of data into our new moments-based formulas, we are able to estimate mutual information and differential entropy efficiently and robustly against affine-transformations of the samples.
일반주제명  
Applied mathematics.
일반주제명  
Information science.
키워드  
Differential privacy
키워드  
Estimation
키워드  
F-divergence
키워드  
Group-fairness
키워드  
Information projection
키워드  
Moments
기타저자  
Harvard University Engineering and Applied Sciences - Applied Math
기본자료저록  
Dissertations Abstracts International. 84-12A.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.
신착도서 더보기
최근 3년간 통계입니다.

소장정보

  • 예약
  • 소재불명신고
  • 나의폴더
  • 우선정리요청
  • 비도서대출신청
  • 야간 도서대출신청
소장자료
등록번호 청구기호 소장처 대출가능여부 대출정보
TF09409 전자도서
마이폴더 부재도서신고 비도서대출신청

* 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

해당 도서를 다른 이용자가 함께 대출한 도서

관련 인기도서

로그인 후 이용 가능합니다.