Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Journal articles
  4. Deep Boltzmann Machines: Rigorous Results at Arbitrary Depth
 
research article

Deep Boltzmann Machines: Rigorous Results at Arbitrary Depth

Alberici, Diego  
•
Contucci, Pierluigi
•
Mingione, Emanuele  
February 22, 2021
Annales Henri Poincaré

A class of deep Boltzmann machines is considered in the simplified framework of a quenched system with Gaussian noise and independent entries. The quenched pressure of a K-layers spin glass model is studied allowing interactions only among consecutive layers. A lower bound for the pressure is found in terms of a convex combination of K Sherrington–Kirkpatrick models and used to study the annealed and replica symmetric regimes of the system. A map with a one-dimensional monomer–dimer system is identified and used to rigorously control the annealed region at arbitrary depth K with the methods introduced by Heilmann and Lieb. The compression of this high-noise region displays a remarkable phenomenon of localisation of the processing layers. Furthermore, a replica symmetric lower bound for the limiting quenched pressure of the model is obtained in a suitable region of the parameters and the replica symmetric pressure is proved to have a unique stationary point.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

Alberici2021_Article_DeepBoltzmannMachinesRigorousR.pdf

Type

Publisher's Version

Version

Published version

Access type

openaccess

License Condition

CC BY

Size

491.24 KB

Format

Adobe PDF

Checksum (MD5)

967770331dec5619498b850dfcbeb308

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés