DeepAI AI Chat
Log In Sign Up

Gaussian Noise is Nearly Instance Optimal for Private Unbiased Mean Estimation

by   Aleksandar Nikolov, et al.

We investigate unbiased high-dimensional mean estimators in differential privacy. We consider differentially private mechanisms whose expected output equals the mean of the input dataset, for every dataset drawn from a fixed convex domain K in ℝ^d. In the setting of concentrated differential privacy, we show that, for every input such an unbiased mean estimator introduces approximately at least as much error as a mechanism that adds Gaussian noise with a carefully chosen covariance. This is true when the error is measured with respect to ℓ_p error for any p ≥ 2. We extend this result to local differential privacy, and to approximate differential privacy, but for the latter the error lower bound holds either for a dataset or for a neighboring dataset. We also extend our results to mechanisms that take i.i.d. samples from a distribution over K and are unbiased with respect to the mean of the distribution.


page 1

page 2

page 3

page 4


HDMM: Optimizing error of high-dimensional statistical queries under differential privacy

In this work we describe the High-Dimensional Matrix Mechanism (HDMM), a...

A Bias-Variance-Privacy Trilemma for Statistical Estimation

The canonical algorithm for differentially private mean estimation is to...

Near Instance-Optimality in Differential Privacy

We develop two notions of instance optimality in differential privacy, i...

Differentially Private Covariance Revisited

In this paper, we present three new error bounds, in terms of the Froben...

Optimal Algorithms for Mean Estimation under Local Differential Privacy

We study the problem of mean estimation of ℓ_2-bounded vectors under the...

A closed form scale bound for the (ε, δ)-differentially private Gaussian Mechanism valid for all privacy regimes

The standard closed form lower bound on σ for providing (ϵ, δ)-different...

Differential privacy for symmetric log-concave mechanisms

Adding random noise to database query results is an important tool for a...