NeurIPS 2021poster71 citations
Instance-optimal Mean Estimation Under Differential Privacy
Ziyue Huang, Yuting Liang, Ke Yi
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.
Mean estimationdifferential privacyinstance optimality
BibTeX
@inproceedings{
huang2021instanceoptimal,
title={Instance-optimal Mean Estimation Under Differential Privacy},
author={Ziyue Huang and Yuting Liang and Ke Yi},
booktitle={Advances in Neural Information Processing Systems},
editor={A. Beygelzimer and Y. Dauphin and P. Liang and J. Wortman Vaughan},
year={2021},
url={https://openreview.net/forum?id=AjgFqUoD4U}
}