Skip to Main content Skip to Navigation
Journal articles

Entropy and mutual information in models of deep neural networks

Abstract : We examine a class of stochastic deep learning models with a tractable method to compute information-theoretic quantities. Our contributions are three-fold: (i) We show how entropies and mutual informations can be derived from heuristic statistical physics methods, under the assumption that weight matrices are independent and orthogonally-invariant. (ii) We extend particular cases in which this result is known to be rigorously exact by providing a proof for two-layers networks with Gaussian random weights, using the recently introduced adaptive interpolation method. (iii) We propose an experiment framework with generative models of synthetic datasets, on which we train deep neural networks with a weight constraint designed so that the assumption in (i) is verified during learning. We study the behavior of entropies and mutual informations throughout learning and conclude that, in the proposed setting, the relationship between compression and generalization remains elusive.
Document type :
Journal articles
Complete list of metadatas

Cited literature [89 references]  Display  Hide  Download

https://hal-cea.archives-ouvertes.fr/cea-01930228
Contributor : Emmanuelle de Laborderie <>
Submitted on : Wednesday, November 21, 2018 - 4:50:52 PM
Last modification on : Wednesday, October 7, 2020 - 3:16:31 AM
Long-term archiving on: : Friday, February 22, 2019 - 3:47:49 PM

File

publi.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Marylou Gabrié, Andre Manoel, Clément Luneau, Jean Barbier, Nicolas Macris, et al.. Entropy and mutual information in models of deep neural networks. Journal of Statistical Mechanics: Theory and Experiment, IOP Publishing, 2019, 19, pp.124014. ⟨10.1088/1742-5468/ab3430⟩. ⟨cea-01930228⟩

Share

Metrics

Record views

174

Files downloads

1001