Low-rank Solutions of Linear Matrix Equations via Procrustes Flow

Stephen Tu, Ross Boczar, Mahdi Soltanolkotabi, Benjamin Recht

Published 2015-07-13Version 1

In this paper we study the problem of recovering an low-rank positive semidefinite 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 $n \times n$ matrix of rank $r$ when the number of measurements exceeds a constant times $nr$.