Limiting free energy of multi-layer generalized linear models

08/28/2021
by   Hong-Bin Chen, et al.
0

We compute the high-dimensional limit of the free energy associated with a multi-layer generalized linear model. Under certain technical assumptions, we identify the limit in terms of a variational formula. The approach is to first show that the limit is a solution to a Hamilton-Jacobi equation whose initial condition is related to the limiting free energy of a model with one fewer layer. Then, we conclude by an iteration.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/12/2021

Statistical inference of finite-rank tensors

We consider a general statistical inference model of finite-rank tensor ...
research
05/16/2017

Learning how to explain neural networks: PatternNet and PatternAttribution

DeConvNet, Guided BackProp, LRP, were invented to better understand deep...
research
02/13/2022

Information Density in Multi-Layer Resistive Memories

Resistive memories store information in a crossbar arrangement of two-te...
research
10/29/2020

Micromagnetics of thin films in the presence of Dzyaloshinskii-Moriya interaction

In this paper, we study the thin-film limit of the micromagnetic energy ...
research
07/20/2020

Estimation for High-Dimensional Multi-Layer Generalized Linear Model – Part I: The Exact MMSE Estimator

This two-part work considers the minimum means square error (MMSE) estim...
research
04/29/2008

Gaussian Processes and Limiting Linear Models

Gaussian processes retain the linear model either as a special case, or ...
research
06/09/2023

Deterministic equivalent of the Conjugate Kernel matrix associated to Artificial Neural Networks

We study the Conjugate Kernel associated to a multi-layer linear-width f...

Please sign up or login with your details

Forgot password? Click here to reset