Guardado en:
Detalles Bibliográficos
Autores principales: Sen, Srimoyee, Vaidya, Varun
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2508.03810
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911686018990080
author Sen, Srimoyee
Vaidya, Varun
author_facet Sen, Srimoyee
Vaidya, Varun
contents Neural Network (NN) architectures that break statistical independence of parameters have been proposed as a new approach for simulating local quantum field theories (QFTs). In the infinite neuron number limit, single-layer NNs can exactly reproduce QFT results. This paper examines the viability of this architecture for perturbative calculations of local QFTs for finite neuron number $N$ using scalar $ϕ^4$ theory in $d$ Euclidean dimensions as an example. We find that the renormalized $O(1/N)$ corrections to two- and four-point correlators yield perturbative series which are sensitive to the ultraviolet cut-off and therefore have a weak convergence. We propose a modification to the architecture to improve this convergence and discuss constraints on the parameters of the theory and the scaling of N which allow us to extract accurate field theory results.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03810
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Viability of perturbative expansion for quantum field theories on neurons
Sen, Srimoyee
Vaidya, Varun
High Energy Physics - Theory
Machine Learning
Neural Network (NN) architectures that break statistical independence of parameters have been proposed as a new approach for simulating local quantum field theories (QFTs). In the infinite neuron number limit, single-layer NNs can exactly reproduce QFT results. This paper examines the viability of this architecture for perturbative calculations of local QFTs for finite neuron number $N$ using scalar $ϕ^4$ theory in $d$ Euclidean dimensions as an example. We find that the renormalized $O(1/N)$ corrections to two- and four-point correlators yield perturbative series which are sensitive to the ultraviolet cut-off and therefore have a weak convergence. We propose a modification to the architecture to improve this convergence and discuss constraints on the parameters of the theory and the scaling of N which allow us to extract accurate field theory results.
title Viability of perturbative expansion for quantum field theories on neurons
topic High Energy Physics - Theory
Machine Learning
url https://arxiv.org/abs/2508.03810