Inference in Deep Networks in High Dimensions

Alyson K. Fletcher, Sundeep Rangan, Philip Schniter

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep generative networks provide a powerful tool for modeling complex data in a wide range of applications. In inverse problems that use these networks as generative priors on data, one must often perform inference of the inputs of the networks from the outputs. Inference is also required for sampling during stochastic training of these generative models. This paper considers inference in a deep stochastic neural network where the parameters (e.g., weights, biases and activation functions) are known and the problem is to estimate the values of the input and hidden units from the output. A novel and computationally tractable inference method called Multi-Layer Vector Approximate Message Passing (ML-VAMP) is presented. Our main contribution shows that the mean-squared error (MSE) of ML-VAMP can be exactly predicted in a certain large system limit. In addition, the MSE achieved by ML-VAMP matches the Bayes optimal value recently postulated by Reeves when certain fixed point equations have unique solutions.

Original languageEnglish (US)
Title of host publication2018 IEEE International Symposium on Information Theory, ISIT 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1884-1888
Number of pages5
ISBN (Print)9781538647806
DOIs
StatePublished - Aug 15 2018
Event2018 IEEE International Symposium on Information Theory, ISIT 2018 - Vail, United States
Duration: Jun 17 2018Jun 22 2018

Publication series

NameIEEE International Symposium on Information Theory - Proceedings
Volume2018-June
ISSN (Print)2157-8095

Other

Other2018 IEEE International Symposium on Information Theory, ISIT 2018
CountryUnited States
CityVail
Period6/17/186/22/18

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Information Systems
  • Modeling and Simulation
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Inference in Deep Networks in High Dimensions'. Together they form a unique fingerprint.

Cite this