Low-rank Solutions of Linear Matrix Equations via Procrustes Flow

arXiv1507.03566MaRDI QIDQ6263552FDOQ6263552

Authors: Stephen Tu, Ross Boczar, Max Simchowitz, Mahdi Soltanolkotabi, Benjamin Recht 

Publication date: 13 July 2015

Abstract: In this paper we study the problem of recovering a low-rank matrix from linear measurements. Our algorithm, which we call Procrustes Flow, starts from an initial estimate obtained by a thresholding scheme followed by gradient descent on a non-convex objective. We show that as long as the measurements obey a standard restricted isometry property, our algorithm converges to the unknown matrix at a geometric rate. In the case of Gaussian measurements, such convergence occurs for a $n_{1}imes{n}_2$ matrix of rank $r$ when the number of measurements exceeds a constant times $(n_1+n_2)r$.

This page was built for publication: Low-rank Solutions of Linear Matrix Equations via Procrustes Flow

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6263552)