# Low-rank Solutions of Linear Matrix Equations via Procrustes Flow

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 n1×n2 matrix of rank r when the number of measurements exceeds a constant times (n1+n2)r.

arXiv

Tags:
Publication Date: July 2015
Conference: Submitted to ICML 2016