Robust Low-Rank Matrix Completion via a New Sparsity-Inducing Regularizer

2023/10/07 by Wang, Zhi-Yong, So, Hing Cheung, Zoubir, Abdelhak M.
#FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2310.04762

Abstract

This paper presents a novel loss function referred to as hybrid ordinary-Welsch (HOW) and a new sparsity-inducing regularizer associated with HOW. We theoretically show that the regularizer is quasiconvex and that the corresponding Moreau envelope is convex. Moreover, the closed-form solution to its Moreau envelope, namely, the proximity operator, is derived. Compared with nonconvex regularizers like the lp-norm with 0

Related

• A framework to generate sparsity-inducing regularizers for enhanced low-rank matrix completion
• Non-Convex Rank/Sparsity Regularization and Local Minima
• Matrix Completion with Nonconvex Regularization: Spectral Operators and Scalable Algorithms
• Nonconvex flexible sparsity regularization: theory and monotone numerical schemes
• A Scalable, Adaptive and Sound Nonconvex Regularizer for Low-rank Matrix Completion