Locally Private Gaussian Estimation
Preprint
Abstract
We study a basic private estimation problem: each of $n$ users draws a single i.i.d. sample from an unknown Gaussian distribution, and the goal is to estimate the mean of this Gaussian distribution while satisfying local differential privacy for each user. Informally, local differential privacy requires that each data point is individually and independently privatized before it is passed to a learning algorithm. Locally private Gaussian estimation is therefore difficult because the data domain is unbounded: users may draw arbitrarily different inputs, but local differential privacy nonetheless mandates that different users have (worst-case) similar privatized output distributions. We provide both adaptive two-round solutions and nonadaptive one-round solutions for locally private Gaussian estimation. We then partially match these upper bounds with an information-theoretic lower bound. This lower bound shows that our accuracy guarantees are tight up to logarithmic factors for all sequentially interactive $(\varepsilon,\delta)$-locally private protocols.
Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Tight Lower Bounds for Differentially Private Selection2017
- Strong Data Processing Inequalities and $\Phi $ -Sobolev Inequalities for Discrete ChannelsIEEE Transactions on Information Theory, 2016
- The Algorithmic Foundations of Differential PrivacyFoundations and Trends® in Theoretical Computer Science, 2014
- Private and Continual Release of StatisticsACM Transactions on Information and System Security, 2011