Sparse Regularization with the $\ell_0$ Norm

Abstract

We consider a minimization problem whose objective function is the sum of a fidelity term, not necessarily convex, and a regularization term defined by a positive regularization parameter λ multiple of the ℓ 0 norm composed with a linear transform. This problem has wide applications in compressed sensing, sparse machine learning and image reconstruction. The goal of this paper is to understand what choices of the regularization parameter can dictate the level of sparsity under the transform for a global minimizer of the resulting regularized objective function. This is a critical issue but it has been left unaddressed. We address it from a geometric viewpoint with which the sparsity partition of the image space of the transform is introduced. Choices of the regularization parameter are specified to ensure that a global minimizer of the corresponding regularized objective function achieves a prescribed level of sparsity under the transform. Results are obtained for the spacial sparsity case in which the transform is the identity map, a case that covers several applications of practical importance, including machine learning, image/signal processing and medical image reconstruction.

Sparse Deep Neural Network for Nonlinear Partial Differential Equations

“…Sparse models can improve accuracy of approximation. Sparse regularization is a popular way to learn the sparse solutions [5,38,39,42]. The readers are referred to [24] for an overview of sparse deep learning.…”