On the Conditions of Sparse Parameter Estimation via Log-Sum Penalty Regularization

Abstract

For high-dimensional sparse parameter estimation problems, Log-Sum Penalty (LSP) regularization effectively reduces the sampling sizes in practice. However, it still lacks theoretical analysis to support the experience from previous empirical study. The analysis of this article shows that, like $\ell_0$-regularization, $O(s)$ sampling size is enough for proper LSP, where $s$ is the non-zero components of the true parameter. We also propose an efficient algorithm to solve LSP regularization problem. The solutions given by the proposed algorithm give consistent parameter estimations under less restrictive conditions than $\ell_1$-regularization.