Sparse representations in nested non-linear models - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Sparse representations in nested non-linear models

Résumé

Following recent contributions in non-linear sparse represen-tations, this work focuses on a particular non-linear model, defined as the nested composition of functions. Recalling that most linear sparse representation algorithms can be straight-forwardly extended to non-linear models, we emphasize that their performance highly relies on an efficient computation of the gradient of the objective function. In the particular case of interest, we propose to resort to a well-known technique from the theory of optimal control to estimate the gradient. This computation is then implemented into the optimization procedure proposed byCan es et al., leading to a non-linear extension of it.
Fichier principal
Vignette du fichier
icassp_soumis.pdf (287.35 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01096254 , version 1 (17-12-2014)

Identifiants

Citer

Angélique Drémeau, Patrick Héas, Cédric Herzet. Sparse representations in nested non-linear models. IEEE International Conference on Speech, Acoustic and Signal Processing (ICASSP), May 2014, Firenze, Italy. ⟨10.1109/ICASSP.2014.6855147⟩. ⟨hal-01096254⟩
260 Consultations
162 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More