Sharp phase transitions for exact support recovery under local differential privacy

by   Cristina Butucea, et al.

We address the problem of variable selection in the Gaussian mean model in ℝ^d under the additional constraint that only privatised data are available for inference. For this purpose, we adopt a recent generalisation of classical minimax theory to the framework of local α-differential privacy. We provide lower and upper bounds on the rate of convergence for the expected Hamming loss over classes of at most s-sparse vectors whose non-zero coordinates are separated from 0 by a constant a>0. As corollaries, we derive necessary and sufficient conditions (up to log factors) for exact recovery and for almost full recovery. When we restrict our attention to non-interactive mechanisms that act independently on each coordinate our lower bound shows that, contrary to the non-private setting, both exact and almost full recovery are impossible whatever the value of a in the high-dimensional regime such that n α^2/ d^2≲ 1. However, in the regime nα^2/d^2≫log(nα^2/d^2)log(d) we can exhibit a sharp critical value a^* (up to a logarithmic factor) such that exact and almost full recovery are possible for all a≫ a^* and impossible for a≤ a^*. We show that these results can be improved when allowing for all non-interactive (that act globally on all coordinates) locally α-differentially private mechanisms in the sense that phase transitions occur at lower levels.


page 1

page 2

page 3

page 4


Goodness-of-fit testing for Hölder continuous densities under local differential privacy

We address the problem of goodness-of-fit testing for Hölder continuous ...

Locally Private Gaussian Estimation

We study a basic private estimation problem: each of n users draws a sin...

Variable selection, monotone likelihood ratio and group sparsity

In the pivotal variable selection problem, we derive the exact non-asymp...

Local differential privacy: Elbow effect in optimal density estimation and adaptation over Besov ellipsoids

We address the problem of non-parametric density estimation under the ad...

Locally differentially private estimation of nonlinear functionals of discrete distributions

We study the problem of estimating non-linear functionals of discrete di...

Local Differential Privacy for Physical Sensor Data and Sparse Recovery

In this work we explore the utility of locally differentially private th...

On the rate of concentration of maxima in Gaussian arrays

Recently in Gao and Stoev (2018) it was established that the concentrati...

Please sign up or login with your details

Forgot password? Click here to reset