Guardado en:
Detalles Bibliográficos
Autores principales: Lee, Hovan, Zhao, Zelong, Booth, George, Ge, Weifeng, Weber, Cedric
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2306.06975
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916626305122304
author Lee, Hovan
Zhao, Zelong
Booth, George
Ge, Weifeng
Weber, Cedric
author_facet Lee, Hovan
Zhao, Zelong
Booth, George
Ge, Weifeng
Weber, Cedric
contents We present SCALINN -- Strongly Correlated Approach with Language Inspired Neural Network -- as a method for solving the Anderson impurity model and reducing the computational cost of dynamical mean-field theory calculations. Inspired by the success of generative Transformer networks in natural language processing, SCALINN utilizes an in-house modified Transformer network in order to learn correlated Matsubara Green's functions, which act as solutions to the impurity model. This is achieved by providing the network with low-cost Matsubara Green's functions, thereby overcoming the computational cost of high accuracy solutions. Across different temperatures and interaction strengths, the performance of SCALINN is demonstrated in both physical observables (spectral function, Matsubara Green's functions, quasi-particle weight), and the mean squared error cost values of the neural network, showcasing the network's ability to accelerate Green's function based calculations of correlated materials.
format Preprint
id arxiv_https___arxiv_org_abs_2306_06975
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A language-inspired machine learning approach for solving strongly correlated problems with dynamical mean-field theory
Lee, Hovan
Zhao, Zelong
Booth, George
Ge, Weifeng
Weber, Cedric
Strongly Correlated Electrons
We present SCALINN -- Strongly Correlated Approach with Language Inspired Neural Network -- as a method for solving the Anderson impurity model and reducing the computational cost of dynamical mean-field theory calculations. Inspired by the success of generative Transformer networks in natural language processing, SCALINN utilizes an in-house modified Transformer network in order to learn correlated Matsubara Green's functions, which act as solutions to the impurity model. This is achieved by providing the network with low-cost Matsubara Green's functions, thereby overcoming the computational cost of high accuracy solutions. Across different temperatures and interaction strengths, the performance of SCALINN is demonstrated in both physical observables (spectral function, Matsubara Green's functions, quasi-particle weight), and the mean squared error cost values of the neural network, showcasing the network's ability to accelerate Green's function based calculations of correlated materials.
title A language-inspired machine learning approach for solving strongly correlated problems with dynamical mean-field theory
topic Strongly Correlated Electrons
url https://arxiv.org/abs/2306.06975