On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians

10/19/2020
by   Ishaq Aden-Ali, et al.
0

We provide sample complexity upper bounds for agnostically learning multivariate Gaussians under the constraint of approximate differential privacy. These are the first finite sample upper bounds for general Gaussians which do not impose restrictions on the parameters of the distribution. Our bounds are near-optimal in the case when the covariance is known to be the identity, and conjectured to be near-optimal in the general case. From a technical standpoint, we provide analytic tools for arguing the existence of global "locally small" covers from local covers of the space. These are exploited using modifications of recent techniques for differentially private hypothesis selection. Our techniques may prove useful for privately learning other distribution classes which do not possess a finite cover.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

05/28/2019

Private Identity Testing for High-Dimensional Distributions

In this work we present novel differentially private identity (goodness-...
05/30/2019

Private Hypothesis Selection

We provide a differentially private algorithm for hypothesis selection. ...
02/21/2020

Private Mean Estimation of Heavy-Tailed Distributions

We give new upper and lower bounds on the minimax sample complexity of d...
02/28/2018

Near-Optimal Sample Complexity Bounds for Maximum Likelihood Estimation of Multivariate Log-concave Densities

We study the problem of learning multivariate log-concave densities with...
05/01/2018

Privately Learning High-Dimensional Distributions

We design nearly optimal differentially private algorithms for learning ...
02/09/2018

Locally Private Hypothesis Testing

We initiate the study of differentially private hypothesis testing in th...
01/11/2021

Flexible Validity Conditions for the Multivariate Matérn Covariance in any Spatial Dimension and for any Number of Components

Flexible multivariate covariance models for spatial data are on demand. ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.