Best Pair Formulation & Accelerated Scheme for Non-convex Principal Component Pursuit
Optimization and Control
2020-12-02 v2 Computer Vision and Pattern Recognition
Numerical Analysis
Numerical Analysis
Abstract
The best pair problem aims to find a pair of points that minimize the distance between two disjoint sets. In this paper, we formulate the classical robust principal component analysis (RPCA) as the best pair; which was not considered before. We design an accelerated proximal gradient scheme to solve it, for which we show global convergence, as well as the local linear rate. Our extensive numerical experiments on both real and synthetic data suggest that the algorithm outperforms relevant baseline algorithms in the literature.
Cite
@article{arxiv.1905.10598,
title = {Best Pair Formulation & Accelerated Scheme for Non-convex Principal Component Pursuit},
author = {Aritra Dutta and Filip Hanzely and Jingwei Liang and Peter Richtárik},
journal= {arXiv preprint arXiv:1905.10598},
year = {2020}
}