arXiv · 1507.03566
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 $n_1 \times n_2$ matrix of rank $r$ when the number of measurements exceeds a constant times $(n_1+n_2)r$.
Explore related subjects
Keep this discovery
Stephen Tu, Ross Boczar, Max Simchowitz, Mahdi Soltanolkotabi, Benjamin Recht. 2015-07-13. Low-rank Solutions of Linear Matrix Equations via Procrustes Flow. https://arxiv.org/abs/1507.03566
Cite the original work for its findings. Save a collection to share your selection of sources.