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.
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal-cea.archives-ouvertes.fr/cea-01447203
Contributor : Emmanuelle de Laborderie <>
Submitted on : Thursday, January 26, 2017 - 4:31:47 PM
Last modification on : Tuesday, May 14, 2019 - 11:05:15 AM
Long-term archiving on: Friday, April 28, 2017 - 8:40:17 AM

File

1701.06981v1.pdf
Files produced by the author(s)

Identifiers

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

Citation

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

Share

Metrics

Record views

354

Files downloads

230