| HAL : hal-00345747, version 1 |
| arXiv : 0812.1869 |
| Fiche détaillée | Récupérer au format |
|
|
|
|
| Convex Sparse Matrix Factorizations |
|
|
| Francis Bach 1Julien Mairal 1 |
|
|
| (09/12/2008) |
|
|
| We present a convex formulation of dictionary learning for sparse signal decomposition. Convexity is obtained by replacing the usual explicit upper bound on the dictionary size by a convex rank-reducing term similar to the trace norm. In particular, our formulation introduces an explicit trade-off between size and sparsity of the decomposition of rectangular matrices. Using a large set of synthetic examples, we compare the estimation abilities of the convex and non-convex approaches, showing that while the convex formulation has a single local minimum, this may lead in some cases to performance which is inferior to the local minima of the non-convex formulation. |
|
|
|
|
|
|
|
|
|
|
| 1 : | WILLOW (INRIA Rocquencourt) |
| INRIA – Ecole Normale Supérieure de Paris - ENS Paris – Ecole des Ponts ParisTech – CNRS : UMR8548 | |
|
|
|
|
|
|
|
|
| Domaine | : | Informatique/Apprentissage Sciences de l'ingénieur/Traitement du signal et de l'image Informatique/Traitement du signal et de l'image |
|
|
| Convex optimization – Machine learning – matrix factorization |
|
|
| Liste des fichiers attachés à ce document : | ||||||||||
|
|
|
| hal-00345747, version 1 | |
| http://hal.archives-ouvertes.fr/hal-00345747 | |
| oai:hal.archives-ouvertes.fr:hal-00345747 | |
| Contributeur : Francis Bach | |
| Soumis le : Mardi 9 Décembre 2008, 17:54:43 | |
| Dernière modification le : Mercredi 10 Décembre 2008, 10:00:48 | |