Sparse Recovery Guarantees from Extreme Eigenvalues Small Deviations

by   Sandrine Dallaporta, et al.

This article provides a new toolbox to derive sparse recovery guarantees from small deviations on extreme singular values or extreme eigenvalues obtained in Random Matrix Theory. This work is based on Restricted Isometry Constants (RICs) which are a pivotal notion in Compressed Sensing and High-Dimensional Statistics as these constants finely assess how a linear operator is conditioned on the set of sparse vectors and hence how it performs in SRSR. While it is an open problem to construct deterministic matrices with apposite RICs, one can prove that such matrices exist using random matrices models. In this paper, we show upper bounds on RICs for Gaussian and Rademacher matrices using state-of-the-art small deviation estimates on their extreme eigenvalues. This allows us to derive a lower bound on the probability of getting SRSR. One benefit of this paper is a direct and explicit derivation of upper bounds on RICs and lower bounds on SRSR from small deviations on the extreme eigenvalues given by Random Matrix theory.


page 1

page 2

page 3

page 4


Asymptotic Analysis for Extreme Eigenvalues of Principal Minors of Random Matrices

Consider a standard white Wishart matrix with parameters n and p. Motiva...

Lower Bound for RIP Constants and Concentration of Sum of Top Order Statistics

Restricted Isometry Property (RIP) is of fundamental importance in the t...

Derandomized compressed sensing with nonuniform guarantees for ℓ_1 recovery

We extend the techniques of Hügel, Rauhut and Strohmer (Found. Comput. M...

Large Deviations of Extreme Eigenvalues of Generalized Sample Covariance Matrices

Very rare events in which the largest eigenvalue of a random matrix is a...

Sparse PCA: Algorithms, Adversarial Perturbations and Certificates

We study efficient algorithms for Sparse PCA in standard statistical mod...

RIP constants for deterministic compressed sensing matrices-beyond Gershgorin

Compressed sensing (CS) is a signal acquisition paradigm to simultaneous...

On Dimension-free Tail Inequalities for Sums of Random Matrices and Applications

In this paper, we present a new framework to obtain tail inequalities fo...