Approximate Message Passing with Restricted Boltzmann Machine Priors - ENSTA Bretagne - École nationale supérieure de techniques avancées Bretagne Accéder directement au contenu
Article Dans Une Revue Journal of Statistical Mechanics: Theory and Experiment Année : 2016

Approximate Message Passing with Restricted Boltzmann Machine Priors

Résumé

Approximate message passing (AMP) has been shown to be an excellent statistical approach to signal inference and compressed sensing problems. The AMP framework provides modularity in the choice of signal prior; here we propose a hierarchical form of the Gauss Bernoulli prior which utilizes a restricted Boltzmann machine (RBM) trained on the signal support to push reconstruction performance beyond that of simple i.i.d. priors for signals whose support can be well represented by a trained binary RBM. We present and analyze two methods of RBM factorization and demonstrate how these affect signal reconstruction performance within our proposed algorithm. Finally, using the MNIST handwritten digit dataset, we show experimentally that using an RBM allows AMP to approach oracle-support performance.
Fichier principal
Vignette du fichier
jstat16_7_073401.pdf (1.21 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01374620 , version 1 (03-10-2016)

Identifiants

Citer

Eric W. Tramel, Angélique Dremeau, Florent Krzakala. Approximate Message Passing with Restricted Boltzmann Machine Priors. Journal of Statistical Mechanics: Theory and Experiment, 2016, 2016, ⟨10.1088/1742-5468/2016/07/073401⟩. ⟨hal-01374620⟩
170 Consultations
175 Téléchargements

Altmetric

Partager

Gmail Facebook Twitter LinkedIn More