ICML 2016poster462 citations

Low-rank Solutions of Linear Matrix Equations via Procrustes Flow

Stephen Tu, Ross Boczar, Max Simchowitz, Mahdi Soltanolkotabi, Ben Recht

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

BibTeX
@InProceedings{pmlr-v48-tu16,
  title = 	 {Low-rank Solutions of Linear Matrix Equations via Procrustes Flow},
  author = 	 {Tu, Stephen and Boczar, Ross and Simchowitz, Max and Soltanolkotabi, Mahdi and Recht, Ben},
  booktitle = 	 {Proceedings of The 33rd International Conference on Machine Learning},
  pages = 	 {964--973},
  year = 	 {2016},
  editor = 	 {Balcan, Maria Florina and Weinberger, Kilian Q.},
  volume = 	 {48},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {New York, New York, USA},
  month = 	 {20--22 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v48/tu16.pdf},
  url = 	 {https://proceedings.mlr.press/v48/tu16.html},
  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 \times n2 matrix of rank r when the number of measurements exceeds a constant times (n1 + n2)r.}
}