Mean Estimation Under Heterogeneous Privacy Demands
IEEE Transactions on Information Theory · 2025-02 · 71 (2) · 1362-1375
DOI: 10.1109/tit.2024.3511498 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Information Theory, 2025-02. Verfasst von Syomantak Chaudhuri und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: Division of Computing and Communication Foundations.
Abstract (Originalsprache)
Differential Privacy (DP) is a well-established framework to quantify privacy loss incurred by any algorithm. Traditional formulations impose a uniform privacy requirement for all users, which is often inconsistent with real-world scenarios in which users dictate their privacy preferences individually. This work considers the problem of mean estimation, where each user can impose their own distinct privacy level. The algorithm we propose for this problem is shown to be minimax optimal and has a near-linear run-time. Our results elicit an interesting saturation phenomenon that occurs. Namely, the privacy requirements of the most stringent users dictate the overall error rates. As a consequence, users with less but differing privacy requirements are all given more privacy than they require, in equal amounts. In other words, these privacy-indifferent users are given a nontrivial degree of privacy for free, without any sacrifice in the performance of the estimator.
Förderung
- Division of Computing and Communication Foundations
Zitieren
APA
Chaudhuri, S., Miagkov, K., & Courtade, T. A. (2025). Mean Estimation Under Heterogeneous Privacy Demands. IEEE Transactions on Information Theory, 71(2), 1362-1375. https://doi.org/10.1109/tit.2024.3511498
Vancouver
Chaudhuri S, Miagkov K, Courtade TA. Mean Estimation Under Heterogeneous Privacy Demands. IEEE Transactions on Information Theory. 2025;71(2):1362-1375. doi:10.1109/tit.2024.3511498
BibTeX
@article{Chaudhuri2025,
author = {Chaudhuri, Syomantak and Miagkov, Konstantin and Courtade, Thomas A.},
title = {Mean Estimation Under Heterogeneous Privacy Demands},
journal = {IEEE Transactions on Information Theory},
year = {2025},
volume = {71},
number = {2},
pages = {1362--1375},
doi = {10.1109/tit.2024.3511498}
}
EUVIMED