Instance-optimal Mean Estimation Under Differential Privacy
Cryptography and Security
2021-11-02 v2 Data Structures and Algorithms
Methodology
Abstract
Mean estimation under differential privacy is a fundamental problem, but worst-case optimal mechanisms do not offer meaningful utility guarantees in practice when the global sensitivity is very large. Instead, various heuristics have been proposed to reduce the error on real-world data that do not resemble the worst-case instance. This paper takes a principled approach, yielding a mechanism that is instance-optimal in a strong sense. In addition to its theoretical optimality, the mechanism is also simple and practical, and adapts to a variety of data characteristics without the need of parameter tuning. It easily extends to the local and shuffle model as well.
Cite
@article{arxiv.2106.00463,
title = {Instance-optimal Mean Estimation Under Differential Privacy},
author = {Ziyue Huang and Yuting Liang and Ke Yi},
journal= {arXiv preprint arXiv:2106.00463},
year = {2021}
}