Timezone: »
We propose a novel class of algorithms for low rank matrix completion. Our approach builds on novel penalty functions on the singular values of the low rank matrix. By exploiting a mixture model representation of this penalty, we show that a suitably chosen set of latent variables enables to derive an Expectation-Maximization algorithm to obtain a Maximum A Posteriori estimate of the completed low rank matrix. The resulting algorithm is an iterative soft-thresholded algorithm which iteratively adapts the shrinkage coefficients associated to the singular values. The algorithm is simple to implement and can scale to large matrices. We provide numerical comparisons between our approach and recent alternatives showing the interest of the proposed approach for low rank matrix completion.
Author Information
Adrien Todeschini (INRIA)
Francois Caron (University of Oxford)
Marie Chavent (Université de Bordeaux II & INRIA)
More from the Same Authors
-
2012 Poster: Bayesian nonparametric models for bipartite graphs »
Francois Caron -
2012 Poster: Bayesian nonparametric models for ranked data »
Francois Caron · Yee Whye Teh -
2012 Oral: Bayesian nonparametric models for bipartite graphs »
Francois Caron -
2009 Workshop: Nonparametric Bayes »
Dilan Gorur · Francois Caron · Yee Whye Teh · David B Dunson · Zoubin Ghahramani · Michael Jordan -
2009 Poster: Bayesian Nonparametric Models on Decomposable Graphs »
Francois Caron · Arnaud Doucet