Tight Performance Bounds for Compressed Sensing With Conventional and Group Sparsity

TL;DR

This paper establishes new theoretical bounds for recovering group sparse signals using convex optimization, extending classical sparse recovery results to group structures and different measurement models.

Contribution

It introduces the group robust null space property (GRNSP), links it to the group restricted isometry property (GRIP), and derives less conservative bounds for group sparse recovery.

Findings

Bounds are less conservative for equal-sized groups.

Results apply to groups of different sizes.

Derived bounds for residual error in all p-norms between 1 and 2.

Abstract

In this paper, we study the problem of recovering a group sparse vector from a small number of linear measurements. In the past the common approach has been to use various "group sparsity-inducing" norms such as the Group LASSO norm for this purpose. By using the theory of convex relaxations, we show that it is also possible to use $\ell_1$-norm minimization for group sparse recovery. We introduce a new concept called group robust null space property (GRNSP), and show that, under suitable conditions, a group version of the restricted isometry property (GRIP) implies the GRNSP, and thus leads to group sparse recovery. When all groups are of equal size, our bounds are less conservative than known bounds. Moreover, our results apply even to situations where where the groups have different sizes. When specialized to conventional sparsity, our bounds reduce to one of the well-known "best possible" conditions for sparse recovery. This relationship between GRNSP and GRIP is new even for conventional sparsity, and substantially streamlines the proofs of some known results. Using this relationship, we derive bounds on the $\ell_p$-norm of the residual error vector for all $p \in [1,2]$, and not just when $p = 2$. When the measurement matrix consists of random samples of a sub-Gaussian random variable, we present bounds on the number of measurements, which are less conservative than currently known bounds.