Multi-Layer Generalized Linear Estimation - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Access content directly
Preprints, Working Papers, ... Year : 2017

Multi-Layer Generalized Linear Estimation

Andre Manoel
  • Function : Author
Marc Mézard


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.
Fichier principal
Vignette du fichier
1701.06981v1.pdf (668.08 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

cea-01447203 , version 1 (26-01-2017)



Andre Manoel, Florent Krzakala, Marc Mézard, Lenka Zdeborová. Multi-Layer Generalized Linear Estimation. 2017. ⟨cea-01447203⟩
255 View
214 Download



Gmail Facebook X LinkedIn More