Smoothed analysis in compressed sensing

TL;DR

This paper demonstrates that adding random perturbations to arbitrary matrices in compressed sensing ensures the robust null space property, enabling unique signal reconstruction with optimal measurement complexity, even with heavy-tailed perturbations.

Contribution

It establishes that perturbed arbitrary matrices satisfy the robust null space property under broad conditions, extending previous results to heavier-tailed distributions and quantifying allowed matrix irregularities.

Findings

Perturbed matrices satisfy robust null space property asymptotically almost surely.

Optimal measurement bounds are achieved for unique reconstruction via -minimization.

Results hold for perturbations with heavy-tailed distributions beyond sub-exponential.

Abstract

Arbitrary matrices $M \in \mathbb{R}^{m \times n}$, randomly perturbed in an additive manner using a random matrix $R \in \mathbb{R}^{m \times n}$, are shown to asymptotically almost surely satisfy the so-called {\sl robust null space property}. Whilst insisting on an asymptotically optimal order of magnitude for $m$ required to attain {\sl unique reconstruction} via $\ell_1$-minimisation algorithms, our results track the level of arbitrariness allowed for the fixed seed matrix $M$ as well as the degree of distributional irregularity allowed for the entries of the perturbing matrix $R$. Starting with sub-gaussian entries for $R$, our results culminate with these allowed to have substantially heavier tails than sub-exponential ones. Throughout this trajectory, two measures control the arbitrariness allowed for $M$; the first is $\|M\|_\infty$ and the second is a localised notion of the Frobenius norm of $M$ (which depends on the sparsity of the signal being reconstructed). A key tool driving our proofs is {\sl Mendelson's small-ball method} ({\em Learning without concentration}, J. ACM, Vol. $62$, $2015$).