Physics-informed neural network model for quantum impurity problems based on Lehmann representation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kakizawa, Fumiya, Terasaki, Satoshi, Shinaoka, Hiroshi
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909407645794304
author Kakizawa, Fumiya
Terasaki, Satoshi
Shinaoka, Hiroshi
author_facet Kakizawa, Fumiya
Terasaki, Satoshi
Shinaoka, Hiroshi
contents We propose a physics-informed neural network (PINN) model to efficiently predict the self-energy of Anderson impurity models (AIMs) based on the Lehmann representation. As an example, we apply the PINN model to a single-orbital AIM (SAIM) for a noninteracting electron bath with a semicircular density of states. Trained across a wide range of onsite Coulomb interactions $U$ and hybridization strengths $V$, the PINN model demonstrates high accuracy in both $U$-$V$ and Matsubara-frequency spaces. Additionally, we investigate the effectiveness of physical constraints implemented in the PINN model. For example, We show that the Lehmann representation allows the PINN model to reduce the maximum test error in an electron filling by a factor of approximately 7.8.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18835
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Physics-informed neural network model for quantum impurity problems based on Lehmann representation
Kakizawa, Fumiya
Terasaki, Satoshi
Shinaoka, Hiroshi
Strongly Correlated Electrons
We propose a physics-informed neural network (PINN) model to efficiently predict the self-energy of Anderson impurity models (AIMs) based on the Lehmann representation. As an example, we apply the PINN model to a single-orbital AIM (SAIM) for a noninteracting electron bath with a semicircular density of states. Trained across a wide range of onsite Coulomb interactions $U$ and hybridization strengths $V$, the PINN model demonstrates high accuracy in both $U$-$V$ and Matsubara-frequency spaces. Additionally, we investigate the effectiveness of physical constraints implemented in the PINN model. For example, We show that the Lehmann representation allows the PINN model to reduce the maximum test error in an electron filling by a factor of approximately 7.8.
title Physics-informed neural network model for quantum impurity problems based on Lehmann representation
topic Strongly Correlated Electrons
url https://arxiv.org/abs/2411.18835