Upper Bounds on the Error of Sparse Vector and Low-Rank Matrix Recovery

TL;DR

This paper derives upper bounds on the error of approximate sparse solutions and low-rank matrix recovery, showing that solutions with dominant components are close to the true solution even when conditions for uniqueness are violated.

Contribution

It provides novel upper bounds on recovery error for approximately sparse vectors and low-rank matrices, extending theoretical guarantees beyond ideal conditions.

Findings

Error bounds depend on small component magnitudes

Bounds are independent of the true solution

Results extend to noisy measurements

Abstract

Suppose that a solution $\widetilde{\mathbf{x}}$ to an underdetermined linear system $\mathbf{b} = \mathbf{A} \mathbf{x}$ is given. $\widetilde{\mathbf{x}}$ is approximately sparse meaning that it has a few large components compared to other small entries. However, the total number of nonzero components of $\widetilde{\mathbf{x}}$ is large enough to violate any condition for the uniqueness of the sparsest solution. On the other hand, if only the dominant components are considered, then it will satisfy the uniqueness conditions. One intuitively expects that $\widetilde{\mathbf{x}}$ should not be far from the true sparse solution $\mathbf{x}_0$. We show that this intuition is the case by providing an upper bound on $\| \widetilde{\mathbf{x}} - \mathbf{x}_0\|$ which is a function of the magnitudes of small components of $\widetilde{\mathbf{x}}$ but independent from $\mathbf{x}_0$. This result is extended to the case that $\mathbf{b}$ is perturbed by noise. Additionally, we generalize the upper bounds to the low-rank matrix recovery problem.