Renormalization-Inspired Effective Field Neural Networks for Scalable Modeling of Classical and Quantum Many-Body Systems

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Xi, Zhao, Yujun, Wan, Chun Yu, Zhang, Yang, Liu, Junwei
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911523694182400
author Liu, Xi
Zhao, Yujun
Wan, Chun Yu
Zhang, Yang
Liu, Junwei
author_facet Liu, Xi
Zhao, Yujun
Wan, Chun Yu
Zhang, Yang
Liu, Junwei
contents We introduce Effective Field Neural Networks (EFNNs), a new architecture based on continued functions -- mathematical tools used in renormalization to handle divergent perturbative series. Our key insight is that neural networks can implement these continued functions directly, providing a principled approach to many-body interactions. Testing on three systems (a classical 3-spin infinite- range model, a continuous classical Heisenberg spin system, and a quantum double exchange model), we find that EFNN outperforms standard deep networks, ResNet, and DenseNet. Most striking is EFNN's generalization: trained on $10 \times 10$ lattices, it accurately predicts behavior on systems up to $40\times 40$ with no additional training -- and the accuracy improves with system size, with a computational time speed-up of $10^{3}$ compared to ED for $40\times 40$ lattice. This demonstrates that EFNN captures the underlying physics rather than merely fitting data, making it valuable beyond many-body problems to any field where renormalization ideas apply.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17665
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Renormalization-Inspired Effective Field Neural Networks for Scalable Modeling of Classical and Quantum Many-Body Systems
Liu, Xi
Zhao, Yujun
Wan, Chun Yu
Zhang, Yang
Liu, Junwei
Computational Physics
Strongly Correlated Electrons
Artificial Intelligence
Quantum Physics
We introduce Effective Field Neural Networks (EFNNs), a new architecture based on continued functions -- mathematical tools used in renormalization to handle divergent perturbative series. Our key insight is that neural networks can implement these continued functions directly, providing a principled approach to many-body interactions. Testing on three systems (a classical 3-spin infinite- range model, a continuous classical Heisenberg spin system, and a quantum double exchange model), we find that EFNN outperforms standard deep networks, ResNet, and DenseNet. Most striking is EFNN's generalization: trained on $10 \times 10$ lattices, it accurately predicts behavior on systems up to $40\times 40$ with no additional training -- and the accuracy improves with system size, with a computational time speed-up of $10^{3}$ compared to ED for $40\times 40$ lattice. This demonstrates that EFNN captures the underlying physics rather than merely fitting data, making it valuable beyond many-body problems to any field where renormalization ideas apply.
title Renormalization-Inspired Effective Field Neural Networks for Scalable Modeling of Classical and Quantum Many-Body Systems
topic Computational Physics
Strongly Correlated Electrons
Artificial Intelligence
Quantum Physics
url https://arxiv.org/abs/2502.17665