Discrete-Aware Matrix Completion via Proximal Gradient
arXiv:2006.04075
Abstract
We present a novel algorithm for the completion of low-rank matrices whose entries are limited to a finite discrete alphabet. The proposed method is based on the recently-emerged proximal gradient (PG) framework of optimization theory, which is applied here to solve a regularized formulation of the completion problem that includes a term enforcing the discrete-alphabet membership of the matrix entries.
arXiv comment5 pages, 2 figures, submitted to an IEEE conference
References in corpus (5)
- Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
- Guaranteed Matrix Completion via Non-convex Factorization
- Discrete Signal Reconstruction by Sum of Absolute Values
- Proximal Gradient Algorithms: Applications in Signal Processing
- Low-Rank Matrix Completion: A Contemporary Survey