Sciweavers

Share
ICASSP
2011
IEEE

Low-rank matrix completion by variational sparse Bayesian learning

8 years 3 days ago
Low-rank matrix completion by variational sparse Bayesian learning
There has been a significant interest in the recovery of low-rank matrices from an incomplete of measurements, due to both theoretical and practical developments demonstrating the wide applicability of the problem. A number of methods have been developed for this recovery problem, however, a principled method for choosing the unknown target rank is generally missing. In this paper, we present a recovery algorithm based on sparse Bayesian learning (SBL) and automatic relevance determination principles. Starting from a matrix factorization formulation and enforcing the low-rank constraint in the estimates as a sparsity constraint, we develop an approach that is very effective in determining the correct rank while providing high recovery performance. We provide empirical results and comparisons with current state-of-the-art methods that illustrate the potential of this approach.
S. Derin Babacan, Martin Luessi, Rafael Molina, Ag
Added 20 Aug 2011
Updated 20 Aug 2011
Type Journal
Year 2011
Where ICASSP
Authors S. Derin Babacan, Martin Luessi, Rafael Molina, Aggelos K. Katsaggelos
Comments (0)
books