Saved in:
Bibliographic Details
Main Author: Terin, Rodrigo Carmo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.18948
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911613484793856
author Terin, Rodrigo Carmo
author_facet Terin, Rodrigo Carmo
contents We develop a gauge-covariant stochastic effective field theory for stability and finite-width effects in deep neural systems. The model uses classical commuting fields: a complex matter field, a real Abelian connection field, and a fictitious stochastic depth variable. Using the Martin--Siggia--Rose--Janssen--de~Dominicis formalism, we derive its functional representation and a two-replica linear-response construction defining the maximal Lyapunov exponent and the amplification factor for the edge of chaos. Finite-width effects appear as perturbative corrections to dressed kernels, and the marginality condition remains unchanged at the order considered for fixed kernel geometry. Numerically, finite-width multilayer perceptrons follow the mean-field instability threshold, and a linear stochastic effective sector reproduces the predicted low-frequency spectral deformation.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18948
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gauge-covariant stochastic neural fields: Stability and finite-width effects
Terin, Rodrigo Carmo
High Energy Physics - Theory
Disordered Systems and Neural Networks
Machine Learning
We develop a gauge-covariant stochastic effective field theory for stability and finite-width effects in deep neural systems. The model uses classical commuting fields: a complex matter field, a real Abelian connection field, and a fictitious stochastic depth variable. Using the Martin--Siggia--Rose--Janssen--de~Dominicis formalism, we derive its functional representation and a two-replica linear-response construction defining the maximal Lyapunov exponent and the amplification factor for the edge of chaos. Finite-width effects appear as perturbative corrections to dressed kernels, and the marginality condition remains unchanged at the order considered for fixed kernel geometry. Numerically, finite-width multilayer perceptrons follow the mean-field instability threshold, and a linear stochastic effective sector reproduces the predicted low-frequency spectral deformation.
title Gauge-covariant stochastic neural fields: Stability and finite-width effects
topic High Energy Physics - Theory
Disordered Systems and Neural Networks
Machine Learning
url https://arxiv.org/abs/2508.18948