TODESCHINI, Adrien; CARON, Francois; CHAVENT, Marie

Métadonnées

Licence d’utilisation du document

TODESCHINI, Adrien
Advanced Learning Evolutionary Algorithms [ALEA]
Institut de Mathématiques de Bordeaux [IMB]
Quality control and dynamic reliability [CQFD]

CARON, Francois
Department of Statistics [Oxford]

CHAVENT, Marie
Institut de Mathématiques de Bordeaux [IMB]
Quality control and dynamic reliability [CQFD]

Langue

Communication dans un congrès

Ce document a été publié dans

NIPS - The Neural Information Processing Systems Conference, 2013-12, South Lake Tahoe. 2013-12, vol. 26, p. 845-853

Curran Associates, Inc.

Résumé en anglais

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.< Réduire

Origine

Importé de hal

Unités de recherche

Institut de Mathématiques de Bordeaux (IMB) - UMR 5251