Tight Recovery Guarantees for Orthogonal Matching Pursuit Under Gaussian Noise

TL;DR

This paper refines the theoretical conditions under which Orthogonal Matching Pursuit reliably recovers sparse signals from noisy measurements, demonstrating the tightness of these conditions through analysis and simulations.

Contribution

It provides a sharper, proven tight sufficient condition for support recovery by OMP under Gaussian noise, improving understanding of its performance limits.

Findings

Sharper sufficient condition for OMP support recovery

Proof of the condition’s tightness for a broad parameter range

Simulations confirming the theoretical results

Abstract

Orthogonal Matching pursuit (OMP) is a popular algorithm to estimate an unknown sparse vector from multiple linear measurements of it. Assuming exact sparsity and that the measurements are corrupted by additive Gaussian noise, the success of OMP is often formulated as exactly recovering the support of the sparse vector. Several authors derived a sufficient condition for exact support recovery by OMP with high probability depending on the signal-to-noise ratio, defined as the magnitude of the smallest non-zero coefficient of the vector divided by the noise level. We make two contributions. First, we derive a slightly sharper sufficient condition for two variants of OMP, in which either the sparsity level or the noise level is known. Next, we show that this sharper sufficient condition is tight, in the following sense: for a wide range of problem parameters, there exist a dictionary of linear measurements and a sparse vector with a signal-to-noise ratio slightly below that of the sufficient condition, for which with high probability OMP fails to recover its support. Finally, we present simulations which illustrate that our condition is tight for a much broader range of dictionaries.