Perfect reconstruction of sparse signals with piecewise continuous nonconvex penalties and nonconvexity control
Preprint
Abstract
We consider compressed sensing formulated as a minimization problem of nonconvex sparse penalties, Smoothly Clipped Absolute deviation (SCAD) and Minimax Concave Penalty (MCP). The nonconvexity of these penalties is controlled by nonconvexity parameters, and L1 penalty is contained as a limit with respect to these parameters. The analytically derived reconstruction limit overcomes that of L1 and the algorithmic limit in the Bayes-optimal setting, when the nonconvexity parameters have suitable values. For the practical usage, we apply the approximate message passing (AMP) to these nonconvex penalties. We show that the performance of AMP is considerably improved by controlling nonconvexity parameters.Keywords
All Related Versions
This publication has 1 reference indexed in Scilit:
- Cross validation in sparse linear regression with piecewise continuous nonconvex penalties and its accelerationJournal of Physics A: Mathematical and Theoretical, 2019