Multi-Layer Generalized Linear Estimation

Abstract : We consider the problem of reconstructing a signal from multi-layered (possibly) non-linear measurements. Using non-rigorous but standard methods from statistical physics we present the Multi-Layer Approximate Message Passing (ML-AMP) algorithm for computing marginal probabilities of the corresponding estimation problem and derive the associated state evolution equations to analyze its performance. We also give the expression of the asymptotic free energy and the minimal information-theoretically achievable reconstruction error. Finally, we present some applications of this measurement model for compressed sensing and perceptron learning with structured matrices/patterns, and for a simple model of estimation of latent variables in an auto-encoder.
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

https://hal-cea.archives-ouvertes.fr/cea-01447203
Contributeur : Emmanuelle De Laborderie <>
Soumis le : jeudi 26 janvier 2017 - 16:31:47
Dernière modification le : jeudi 11 janvier 2018 - 06:22:09
Document(s) archivé(s) le : vendredi 28 avril 2017 - 08:40:17

Fichier

1701.06981v1.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : cea-01447203, version 1
  • ARXIV : 1701.06981

Collections

Citation

Andre Manoel, Florent Krzakala, Marc Mézard, Lenka Zdeborová. Multi-Layer Generalized Linear Estimation. t17/012. 5 pages, 1 figure. 2017. 〈cea-01447203〉

Partager

Métriques

Consultations de la notice

129

Téléchargements de fichiers

39