Group-Sparse Signal Denoising: Non-Convex Regularization, Convex Optimization

Abstract

Convex optimization with sparsity-promoting convex regularization is a standard approach for estimating sparse signals in noise. In order to promote sparsity more strongly than convex regularization, it is also standard practice to employ non-convex optimization. In this paper, we take a third approach. We utilize a non-convex regularization term chosen such that the total cost function (consisting of data consistency and regularization terms) is convex. Therefore, sparsity is more strongly promoted than in the standard convex formulation, but without sacrificing the attractive aspects of convex optimization (unique minimum, robust algorithms, etc.). We use this idea to improve the recently developed 'overlapping group shrinkage' (OGS) algorithm for the denoising of group-sparse signals. The algorithm is applied to the problem of speech enhancement with favorable results in terms of both SNR and perceptual quality.

14 pages, 11 figures

Cited by in corpus (18)

• Sparse Regularization via Convex Analysis
• Sparsity-based Algorithm for Detecting Faults in Rotating Machines
• Total Variation Denoising via the Moreau Envelope
• Enhanced Low-Rank Matrix Approximation
• Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
• Repetitive Transients Extraction Algorithm for Detecting Bearing Faults
• Detection of Faults in Rotating Machinery Using Periodic Time-Frequency Sparsity
• Enhanced Sparsity by Non-Separable Regularization
• On the Adversarial Robustness of LASSO Based Feature Selection
• Sparsity-based Correction of Exponential Artifacts
• Optimum window length of Savitzky-Golay filters with arbitrary order
• Basis Pursuit Denoise with Nonsmooth Constraints
• Total Variation with Overlapping Group Sparsity and Lp Quasinorm for Infrared Image Deblurring under Salt-and-Pepper Noise
• Fast Iteratively Reweighted Least Squares Algorithms for Analysis-Based Sparsity Reconstruction
• Sparsity Within and Across Overlapping Groups
• An Optimization Framework with Flexible Inexact Inner Iterations for Nonconvex and Nonsmooth Programming
• Sparse time-frequency representation via atomic norm minimization
• A Convex-Nonconvex Framework for Enhancing Minimization Induced Penalties