File(s) under permanent embargo
Riemannian optimization with subspace tracking for low-rank recovery
conference contribution
posted on 2016-10-31, 00:00 authored by Q Li, W Niu, Gang LiGang Li, J Tan, G Xiong, L GuoLow-rank matrix recovery (MR) has been widely used in data analysis and dimensionality reduction. As a direct heuristic to MR, convex relaxation is usually degraded by the repeated calling of singular value decomposition (SVD), especially in large-scale applications. In this paper, we propose a novel Riemannian optimization method (ROAM) for MR problem by exploiting the Riemannian geometry of the searching space. In particular, ROAM utilizes an efficient subspace tracking schema that automatically detects the unknown rank to identify the preferable geometry space. Moreover, a gradient-based optimization algorithm is proposed to obtain the latent low-rank component, which avoids the expensive full dimension of SVD. More significantly, ROAM algorithm is proved to converge under mild assumptions, which also verifies the effectiveness of ROAM. Extensive empirical results demonstrate the improved accuracy and efficiency of ROAM over convex-relaxation approaches.
History
Event
Neural Networks. IEEE International Joint Conference (2016 : Vancouver, Canada)Pagination
3280 - 3287Publisher
IEEELocation
Vancouver, CanadaPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2016-07-24End date
2016-07-29ISBN-13
9781509006205Language
engPublication classification
E Conference publication; E1 Full written paper - refereedCopyright notice
2016, IEEETitle of proceedings
IJCNN 2016: Proceedings of the IEEE International Joint Conference on Neural NetworksUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC