Log In Sign Up

Covariance-Aware Private Mean Estimation Without Private Covariance Estimation

by   Gavin Brown, et al.

We present two sample-efficient differentially private mean estimators for d-dimensional (sub)Gaussian distributions with unknown covariance. Informally, given n ≳ d/α^2 samples from such a distribution with mean μ and covariance Σ, our estimators output μ̃ such that μ̃- μ_Σ≤α, where ·_Σ is the Mahalanobis distance. All previous estimators with the same guarantee either require strong a priori bounds on the covariance matrix or require Ω(d^3/2) samples. Each of our estimators is based on a simple, general approach to designing differentially private mechanisms, but with novel technical steps to make the estimator private and sample-efficient. Our first estimator samples a point with approximately maximum Tukey depth using the exponential mechanism, but restricted to the set of points of large Tukey depth. Proving that this mechanism is private requires a novel analysis. Our second estimator perturbs the empirical mean of the data set with noise calibrated to the empirical covariance, without releasing the covariance itself. Its sample complexity guarantees hold more generally for subgaussian distributions, albeit with a slightly worse dependence on the privacy parameter. For both estimators, careful preprocessing of the data is required to satisfy differential privacy.


page 1

page 2

page 3

page 4


A Private and Computationally-Efficient Estimator for Unbounded Gaussians

We give the first polynomial-time, polynomial-sample, differentially pri...

CoinPress: Practical Private Mean and Covariance Estimation

We present simple differentially private estimators for the mean and cov...

Private Robust Estimation by Stabilizing Convex Relaxations

We give the first polynomial time and sample (ϵ, δ)-differentially priva...

A Differentially Private Kernel Two-Sample Test

Kernel two-sample testing is a useful statistical tool in determining wh...

Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanism

We give the first polynomial-time algorithm to estimate the mean of a d-...

Differentially Private Estimation via Statistical Depth

Constructing a differentially private (DP) estimator requires deriving t...

Concentration of the exponential mechanism and differentially private multivariate medians

We prove concentration inequalities for the output of the exponential me...