arXiv · 2508.18948
Gauge-covariant stochastic neural fields: Stability and finite-width effects
Abstract
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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Rodrigo Carmo Terin. 2025-08-26. Gauge-covariant stochastic neural fields: Stability and finite-width effects. https://doi.org/10.1038/s41598-026-47071-y
Cite the original work for its findings. Save a collection to share your selection of sources.