Deep Unrolling for Nonconvex Robust Principal Component Analysis
Abstract
We design algorithms for Robust Principal Component Analysis (RPCA) which consists in decomposing a matrix into the sum of a low rank matrix and a sparse matrix. We propose a deep unrolled algorithm based on an accelerated alternating projection algorithm which aims to solve RPCA in its nonconvex form. The proposed procedure combines benefits of deep neural networks and the interpretability of the original algorithm and it automatically learns hyperparameters. We demonstrate the unrolled algorithm's effectiveness on synthetic datasets and also on a face modeling problem, where it leads to both better numerical and visual performances.
Keywords
Cite
@article{arxiv.2307.05893,
title = {Deep Unrolling for Nonconvex Robust Principal Component Analysis},
author = {Elizabeth Z. C. Tan and Caroline Chaux and Emmanuel Soubies and Vincent Y. F. Tan},
journal= {arXiv preprint arXiv:2307.05893},
year = {2023}
}
Comments
7 pages, 3 figures; Accepted to the 2023 IEEE International Workshop on Machine Learning for Signal Processing