Please use this identifier to cite or link to this item: http://hdl.handle.net/1783.1/79599

Efficient Algorithms on Robust Low-Rank Matrix Completion Against Outliers

Authors Zhao, Licheng HKUST affiliated (currently or previously)
Babu, Prabhu Sing HKUST affiliated (currently or previously)
Palomar, Daniel Perez View this author's profile
Issue Date 2016
Source IEEE Transactions on Signal Processing , v. 64, (18), September 2016, article number 7478144, p. 4767-4780
Summary This paper considers robust low-rank matrix completion in the presence of outliers. The objective is to recover a low-rank data matrix from a small number of noisy observations. We exploit the bilinear factorization formulation and develop a novel algorithm fully utilizing parallel computing resources. Our main contributions are i) providing two smooth loss functions that promote robustness against two types of outliers, namely, dense outliers drawn from some elliptical distribution and sparse spike-like outliers with small additive Gaussian noise; and ii) an efficient algorithm with provable convergence to a stationary solution based on a parallel update scheme. Numerical results show that the proposed algorithm obtains a better solution with faster convergence speed than the benchmark algorithms in both synthetic and real data scenarios.
Subjects
ISSN 1053-587X
Language English
Format Article
Access View full-text via DOI
View full-text via Scopus
View full-text via Web of Science
Find@HKUST