Best Pair Formulation & Accelerated Scheme for Non-convex Principal Component Pursuit

DOI10.1109/TSP.2020.3011024MaRDI QIDQ6319364arXivFDO

Authors Aritra Dutta, Filip Hanzely, Jingwei Liang, Peter Richtárik

Publication date 25 May 2019

Published in arXiv

Full work available at URL https://doi.org/10.1109/TSP.2020.3011024

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

arXiv classification

cs.CVcs.NAmath.NAmath.OC

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.

This page was built for publication: Best Pair Formulation & Accelerated Scheme for Non-convex Principal Component Pursuit

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6319364)