Instance-optimal Mean Estimation Under Differential Privacy
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- June 2021
- DOI:
- 10.48550/arXiv.2106.00463
- arXiv:
- arXiv:2106.00463
- Bibcode:
- 2021arXiv210600463H
- Keywords:
-
- Computer Science - Cryptography and Security;
- Computer Science - Data Structures and Algorithms;
- Statistics - Methodology