The phase diagram of compressed sensing with $\ell_0$-norm regularization

TL;DR

This paper introduces two new algorithms based on $ extless lzero extgreater$-norm regularization for noiseless compressed sensing, outperforming LASSO in high compression regimes, with rigorous analysis and phase diagram characterization.

Contribution

It proposes novel $ extless lzero extgreater$-norm algorithms using Approximate Survey Propagation, providing exact phase diagrams and a statistical physics analysis of the model.

Findings

Algorithms outperform LASSO at high compression rates.

Exact prediction of perfect reconstruction regimes via State Evolution.

Identification of replica symmetric and 1RSB states in the model.

Abstract

Noiseless compressive sensing is a two-steps setting that allows for undersampling a sparse signal and then reconstructing it without loss of information. The LASSO algorithm, based on $\lone$ regularization, provides an efficient and robust to address this problem, but it fails in the regime of very high compression rate. Here we present two algorithms based on $\lzero$-norm regularization instead that outperform the LASSO in terms of compression rate in the Gaussian design setting for measurement matrix. These algorithms are based on the Approximate Survey Propagation, an algorithmic family within the Approximate Message Passing class. In the large system limit, they can be rigorously tracked through State Evolution equations and it is possible to exactly predict the range compression rates for which perfect signal reconstruction is possible. We also provide a statistical physics analysis of the $\lzero$-norm noiseless compressive sensing model. We show the existence of both a replica symmetric state and a 1-step replica symmmetry broken (1RSB) state for sufficiently low $\lzero$-norm regularization. The recovery limits of our algorithms are linked to the behavior of the 1RSB solution.