English

A Novel Regularization Based on the Error Function for Sparse Recovery

Numerical Analysis 2021-03-10 v1 Numerical Analysis Optimization and Control

Abstract

Regularization plays an important role in solving ill-posed problems by adding extra information about the desired solution, such as sparsity. Many regularization terms usually involve some vector norm, e.g., L1L_1 and L2L_2 norms. In this paper, we propose a novel regularization framework that uses the error function to approximate the unit step function. It can be considered as a surrogate function for the L0L_0 norm. The asymptotic behavior of the error function with respect to its intrinsic parameter indicates that the proposed regularization can approximate the standard L0L_0, L1L_1 norms as the parameter approaches to 00 and ,\infty, respectively. Statistically, it is also less biased than the L1L_1 approach. We then incorporate the error function into either a constrained or an unconstrained model when recovering a sparse signal from an under-determined linear system. Computationally, both problems can be solved via an iterative reweighted L1L_1 (IRL1) algorithm with guaranteed convergence. A large number of experimental results demonstrate that the proposed approach outperforms the state-of-the-art methods in various sparse recovery scenarios.

Keywords

Cite

@article{arxiv.2007.02784,
  title  = {A Novel Regularization Based on the Error Function for Sparse Recovery},
  author = {Weihong Guo and Yifei Lou and Jing Qin and Ming Yan},
  journal= {arXiv preprint arXiv:2007.02784},
  year   = {2021}
}