Guardado en:
Detalles Bibliográficos
Autores principales: McNaughton, Jake, Hibat-Allah, Mohamed
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2507.18700
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911075762438144
author McNaughton, Jake
Hibat-Allah, Mohamed
author_facet McNaughton, Jake
Hibat-Allah, Mohamed
contents Neural-network quantum states (NQS) are powerful neural-network ansätzes that have emerged as promising tools for studying quantum many-body physics through the lens of the variational principle. These architectures are known to be systematically improvable by increasing the number of parameters. Here we demonstrate an Adaptive scheme to optimize NQSs, through the example of recurrent neural networks (RNN), using a fraction of the computation cost while reducing training fluctuations and improving the quality of variational calculations targeting ground states of prototypical models in one- and two-spatial dimensions. This Adaptive technique reduces the computational cost through training small RNNs and reusing them to initialize larger RNNs. This work opens up the possibility for optimizing graphical processing unit (GPU) resources deployed in large-scale NQS simulations.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18700
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Neural Quantum States: A Recurrent Neural Network Perspective
McNaughton, Jake
Hibat-Allah, Mohamed
Disordered Systems and Neural Networks
Strongly Correlated Electrons
Machine Learning
Computational Physics
Quantum Physics
Neural-network quantum states (NQS) are powerful neural-network ansätzes that have emerged as promising tools for studying quantum many-body physics through the lens of the variational principle. These architectures are known to be systematically improvable by increasing the number of parameters. Here we demonstrate an Adaptive scheme to optimize NQSs, through the example of recurrent neural networks (RNN), using a fraction of the computation cost while reducing training fluctuations and improving the quality of variational calculations targeting ground states of prototypical models in one- and two-spatial dimensions. This Adaptive technique reduces the computational cost through training small RNNs and reusing them to initialize larger RNNs. This work opens up the possibility for optimizing graphical processing unit (GPU) resources deployed in large-scale NQS simulations.
title Adaptive Neural Quantum States: A Recurrent Neural Network Perspective
topic Disordered Systems and Neural Networks
Strongly Correlated Electrons
Machine Learning
Computational Physics
Quantum Physics
url https://arxiv.org/abs/2507.18700