Restricted Boltzmann machine learning for solving strongly correlated quantum systems

被引:226
作者
Nomura, Yusuke [1 ]
Darmawan, Andrew S. [1 ]
Yamaji, Youhei [1 ,2 ]
Imada, Masatoshi [1 ]
机构
[1] Univ Tokyo, Dept Appl Phys, Bunkyo Ku, 7-3-1 Hongo, Tokyo 1138656, Japan
[2] JST, PRESTO, Bunkyo Ku, 7-3-1 Hongo, Tokyo 1138656, Japan
关键词
VARIATIONAL MONTE-CARLO; ANTIFERROMAGNETIC HEISENBERG-MODEL; RENORMALIZATION-GROUP METHOD; ENTANGLED PAIR STATES; MATRIX PRODUCT STATES; MANY-BODY PROBLEM; GROUND-STATE; ELECTRON-SYSTEMS; NEURAL-NETWORKS; SQUARE LATTICE;
D O I
10.1103/PhysRevB.96.205152
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
We develop a machine learning method to construct accurate ground-state wave functions of strongly interacting and entangled quantum spin as well as fermionic models on lattices. A restricted Boltzmann machine algorithm in the form of an artificial neural network is combined with a conventional variational Monte Carlo method with pair product (geminal) wave functions and quantum number projections. The combination allows an application of the machine learning scheme to interacting fermionic systems. The combined method substantially improves the accuracy beyond that ever achieved by each method separately, in the Heisenberg as well as Hubbard models on square lattices, thus proving its power as a highly accurate quantum many-body solver.
引用
收藏
页数:8
相关论文
共 50 条
[11]   Spectral dynamics of learning in restricted Boltzmann machines [J].
Decelle, A. ;
Fissore, G. ;
Furtlehner, C. .
EPL, 2017, 119 (06)
[12]   Supervised Deep Restricted Boltzmann Machine for Estimation of Concrete [J].
Rafiei, Mohammad Hossein ;
Khushefati, Waleed H. ;
Demirboga, Ramazan ;
Adeli, Hojjat .
ACI MATERIALS JOURNAL, 2017, 114 (02) :237-244
[13]   Neurosymbolic Reasoning and Learning with Restricted Boltzmann Machines [J].
Tran, Son N. ;
Garcez, Artur d'Avila .
THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 5, 2023, :6558-6565
[14]   Machine learning effective models for quantum systems [J].
Rigo, Jonas B. ;
Mitchell, Andrew K. .
PHYSICAL REVIEW B, 2020, 101 (24)
[15]   Self-learning projective quantum Monte Carlo simulations guided by restricted Boltzmann machines [J].
Pilati, S. ;
Inack, E. M. ;
Pieri, P. .
PHYSICAL REVIEW E, 2019, 100 (04)
[16]   Helping restricted Boltzmann machines with quantum-state representation by restoring symmetry [J].
Nomura, Yusuke .
JOURNAL OF PHYSICS-CONDENSED MATTER, 2021, 33 (17)
[17]   Quantum Many-Body Solver Using Artificial Neural Networks and its Applications to Strongly Correlated Electron Systems [J].
Nomura, Yusuke ;
Imada, Masatoshi .
JOURNAL OF THE PHYSICAL SOCIETY OF JAPAN, 2025, 94 (03)
[18]   Classification model of restricted Boltzmann machine based on reconstruction error [J].
Yin, Jing ;
Lv, Jiancheng ;
Sang, Yongsheng ;
Guo, Jixiang .
NEURAL COMPUTING & APPLICATIONS, 2018, 29 (11) :1171-1186
[19]   Architecture and Implementation of a Restricted Boltzmann Machine for Handwritten Digits Recognition [J].
Toulgaridis, Nikolaos ;
Bougioukou, Eleni ;
Antonakopoulos, Theodore .
2017 6TH INTERNATIONAL CONFERENCE ON MODERN CIRCUITS AND SYSTEMS TECHNOLOGIES (MOCAST), 2017,
[20]   Thermodynamics of Restricted Boltzmann Machines and Related Learning Dynamics [J].
A. Decelle ;
G. Fissore ;
C. Furtlehner .
Journal of Statistical Physics, 2018, 172 :1576-1608