Approximate message passing for nonconvex sparse regularization with stability and asymptotic analysis
This work provides theoretical insights into nonconvex optimization for sparse regularization, with potential applications in signal processing and statistics, though it is incremental as it builds on existing AMP and replica analysis frameworks.
The paper tackles the problem of linear regression with nonconvex SCAD regularization under Gaussian data, showing that the proposed SCAD-AMP algorithm achieves optimal performance predicted by replica methods for large systems, with statistical representation error lower than L1-based methods.
We analyse a linear regression problem with nonconvex regularization called smoothly clipped absolute deviation (SCAD) under an overcomplete Gaussian basis for Gaussian random data. We propose an approximate message passing (AMP) algorithm considering nonconvex regularization, namely SCAD-AMP, and analytically show that the stability condition corresponds to the de Almeida--Thouless condition in spin glass literature. Through asymptotic analysis, we show the correspondence between the density evolution of SCAD-AMP and the replica symmetric solution. Numerical experiments confirm that for a sufficiently large system size, SCAD-AMP achieves the optimal performance predicted by the replica method. Through replica analysis, a phase transition between replica symmetric (RS) and replica symmetry breaking (RSB) region is found in the parameter space of SCAD. The appearance of the RS region for a nonconvex penalty is a significant advantage that indicates the region of smooth landscape of the optimization problem. Furthermore, we analytically show that the statistical representation performance of the SCAD penalty is better than that of L1-based methods, and the minimum representation error under RS assumption is obtained at the edge of the RS/RSB phase. The correspondence between the convergence of the existing coordinate descent algorithm and RS/RSB transition is also indicated.