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...
Contents Info
Estimation and Optimization of Information Measures with Applications to Fairness and Differential Privacy- [electronic resource]
Material Type  
 단행본
 
0016932450
Date and Time of Latest Transaction  
20240214100500
ISBN  
9798379604790
DDC  
519
Author  
Alghamdi, Wael Mohammed A.
Title/Author  
Estimation and Optimization of Information Measures with Applications to Fairness and Differential Privacy - [electronic resource]
Publish Info  
[S.l.]: : Harvard University., 2023
Publish Info  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
Material Info  
1 online resource(373 p.)
General Note  
Source: Dissertations Abstracts International, Volume: 84-12, Section: A.
General Note  
Advisor: Calmon, Flavio.
학위논문주기  
Thesis (Ph.D.)--Harvard University, 2023.
Restrictions on Access Note  
This item must not be sold to any third party vendors.
Abstracts/Etc  
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.
Subject Added Entry-Topical Term  
Applied mathematics.
Subject Added Entry-Topical Term  
Information science.
Index Term-Uncontrolled  
Differential privacy
Index Term-Uncontrolled  
Estimation
Index Term-Uncontrolled  
F-divergence
Index Term-Uncontrolled  
Group-fairness
Index Term-Uncontrolled  
Information projection
Index Term-Uncontrolled  
Moments
Added Entry-Corporate Name  
Harvard University Engineering and Applied Sciences - Applied Math
Host Item Entry  
Dissertations Abstracts International. 84-12A.
Host Item Entry  
Dissertation Abstract International
Electronic Location and Access  
로그인 후 원문을 볼 수 있습니다.
소장사항  
202402 2024
New Books MORE
최근 3년간 통계입니다.

Detail Info.

  • Reservation
  • Not Exist
  • My Folder
  • First Request
  • 비도서대출신청
  • 야간 도서대출신청
Material
Reg No. Call No. Location Status Lend Info
TF09409 전자도서
마이폴더 부재도서신고 비도서대출신청

* Reservations are available in the borrowing book. To make reservations, Please click the reservation button

해당 도서를 다른 이용자가 함께 대출한 도서

Related Popular Books

로그인 후 이용 가능합니다.