papers AI Learner
The Github is limit! Click to go to the new site.

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

2019-05-25
Aritra Dutta, Filip Hanzely, Jingwei Liang, Peter Richtárik

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.10598

PDF

http://arxiv.org/pdf/1905.10598


Similar Posts

Comments