The Sample Complexity of Robust Covariance Testing

12/31/2020
by   Ilias Diakonikolas, et al.
12

We study the problem of testing the covariance matrix of a high-dimensional Gaussian in a robust setting, where the input distribution has been corrupted in Huber's contamination model. Specifically, we are given i.i.d. samples from a distribution of the form Z = (1-ϵ) X + ϵ B, where X is a zero-mean and unknown covariance Gaussian 𝒩(0, Σ), B is a fixed but unknown noise distribution, and ϵ>0 is an arbitrarily small constant representing the proportion of contamination. We want to distinguish between the cases that Σ is the identity matrix versus γ-far from the identity in Frobenius norm. In the absence of contamination, prior work gave a simple tester for this hypothesis testing task that uses O(d) samples. Moreover, this sample upper bound was shown to be best possible, within constant factors. Our main result is that the sample complexity of covariance testing dramatically increases in the contaminated setting. In particular, we prove a sample complexity lower bound of Ω(d^2) for ϵ an arbitrarily small constant and γ = 1/2. This lower bound is best possible, as O(d^2) samples suffice to even robustly learn the covariance. The conceptual implication of our result is that, for the natural setting we consider, robust hypothesis testing is at least as hard as robust estimation.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/10/2018

Testing Identity of Multidimensional Histograms

We investigate the problem of identity testing for multidimensional hist...
05/31/2018

Efficient Algorithms and Lower Bounds for Robust Linear Regression

We study the problem of high-dimensional linear regression in a robust m...
05/16/2022

Robust Testing in High-Dimensional Sparse Models

We consider the problem of robustly testing the norm of a high-dimension...
03/31/2020

Covariance-Robust Dynamic Watermarking

Attack detection and mitigation strategies for cyberphysical systems (CP...
11/19/2020

Estimation of Shortest Path Covariance Matrices

We study the sample complexity of estimating the covariance matrix Σ∈ℝ^d...
06/16/2020

Reverse Lebesgue and Gaussian isoperimetric inequalities for parallel sets with applications

The r-parallel set of a measurable set A ⊆ℝ^d is the set of all points w...
06/06/2022

Communication-constrained hypothesis testing: Optimality, robustness, and reverse data processing inequalities

We study hypothesis testing under communication constraints, where each ...