Matrix completion by singular value thresholding: sharp bounds - Centre de Recherche en Économie et Statistique Accéder directement au contenu
Article Dans Une Revue Electronic Journal of Statistics Année : 2015

Matrix completion by singular value thresholding: sharp bounds

Résumé

We consider the matrix completion problem where the aim is to esti-mate a large data matrix for which only a relatively small random subset of its entries is observed. Quite popular approaches to matrix completion problem are iterative thresholding methods. In spite of their empirical success, the theoretical guarantees of such iterative thresholding methods are poorly understood. The goal of this paper is to provide strong theo-retical guarantees, similar to those obtained for nuclear-norm penalization methods and one step thresholding methods, for an iterative thresholding algorithm which is a modification of the softImpute algorithm. An im-portant consequence of our result is the exact minimax optimal rates of convergence for matrix completion problem which were known until know only up to a logarithmic factor.
Fichier principal
Vignette du fichier
tresholding_12_Jan.pdf (244.67 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01111757 , version 1 (30-01-2015)

Identifiants

Citer

Olga Klopp. Matrix completion by singular value thresholding: sharp bounds. Electronic Journal of Statistics , 2015, 9 (2), pp. 2348--2369. ⟨hal-01111757⟩
154 Consultations
510 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More