Riemannian pursuit for big matrix recovery
- Publication Type:
- Conference Proceeding
- Citation:
- 31st International Conference on Machine Learning, ICML 2014, 2014, 4 pp. 3467 - 3483
- Issue Date:
- 2014-01-01
Open Access
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
Copyright © (2014) by the International Machine Learning Society (IMLS) All rights reserved. Low rank matrix recovery is a fundamental task in many real-world applications. The perfor-mance of existing methods, however, deteriorates significantly when applied to ill-conditioned or large-scale matrices. In this paper, we therefore propose an efficient method, called Riemannian Pursuit (RP), that aims to address these two problems simultaneously. Our method consists of a sequence of fixed-rank optimization problems. Each subproblem, solved by a nonlinear Rieman-nian conjugate gradient method, aims to correct the solution in the most important subspace of increasing size. Theoretically, RP converges linearly under mild conditions and experimental results show that it substantially outperforms existing methods when applied to large-scale and ill-conditioned matrices.
Please use this identifier to cite or link to this item: