Hybrid convolutional neural network and projected entangled pair states wave functions for quantum many-particle states

Neural networks have been used as variational wave functions for quantum many-particle problems. It has been shown that the correct sign structure is crucial to obtain highly-accurate ground state energies. In this paper, we propose a hybrid wave function combining the convolutional neural network (...

Full description

Saved in:
Bibliographic Details
Published in:Physical review. B 2021-01, Vol.103 (3), p.035138, Article 035138
Main Authors: Liang, Xiao, Dong, Shao-Jun, He, Lixin
Format: Article
Language:English
Subjects:
Artificial neural networks
Neural networks
Wave functions
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural networks have been used as variational wave functions for quantum many-particle problems. It has been shown that the correct sign structure is crucial to obtain highly-accurate ground state energies. In this paper, we propose a hybrid wave function combining the convolutional neural network (CNN) and projected entangled pair states (PEPS), in which the sign structures are determined by the PEPS, and the amplitudes of the wave functions are provided by CNN. We benchmark the ansatz on the highly frustrated spin-1/2 J1−J2 model. We show that the achieved ground energies are competitive with state-of-the-art results.
ISSN:2469-9950
2469-9969
DOI:10.1103/PhysRevB.103.035138