A Nonstochastic Optimization Algorithm for Neural-Network Quantum States

被引:3
|
作者
Li, Xiang [1 ,2 ]
Huang, Jia-Cheng [1 ,2 ]
Zhang, Guang-Ze [1 ,2 ]
Li, Hao-En [1 ,2 ]
Cao, Chang-Su [1 ,2 ,3 ]
Lv, Dingshun [3 ]
Hu, Han-Shi [1 ,2 ]
机构
[1] Tsinghua Univ, Minist Educ, Dept Chem, Beijing 100084, Peoples R China
[2] Tsinghua Univ, Engn Res Ctr Adv Rare Earth Mat, Minist Educ, Beijing 100084, Peoples R China
[3] ByteDance Res, Beijing 100089, Peoples R China
基金
中国国家自然科学基金;
关键词
BATH CONFIGURATION-INTERACTION; MONTE-CARLO;
D O I
10.1021/acs.jctc.3c00831
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
Neural-network quantum states (NQS) employ artificial neural networks to encode many-body wave functions in a second quantization through variational Monte Carlo (VMC). They have recently been applied to accurately describe electronic wave functions of molecules and have shown the challenges in efficiency compared with traditional quantum chemistry methods. Here, we introduce a general nonstochastic optimization algorithm for NQS in chemical systems, which deterministically generates a selected set of important configurations simultaneously with energy evaluation of NQS. This method bypasses the need for Markov-chain Monte Carlo within the VMC framework, thereby accelerating the entire optimization process. Furthermore, this newly developed nonstochastic optimization algorithm for NQS offers comparable or superior accuracy compared to its stochastic counterpart and ensures more stable convergence. The application of this model to test molecules exhibiting strong electron correlations provides further insight into the performance of NQS in chemical systems and opens avenues for future enhancements.
引用
收藏
页码:8156 / 8165
页数:10
相关论文
共 50 条
  • [31] Neural-network variational quantum algorithm for simulating many-body dynamics
    Lee, Chee Kong
    Patil, Pranay
    Zhang, Shengyu
    Hsieh, Chang Yu
    PHYSICAL REVIEW RESEARCH, 2021, 3 (02):
  • [32] Reliability optimization design using a hybridized genetic algorithm with a neural-network technique
    Lee, C
    Gen, M
    Kuo, W
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2001, E84A (02) : 627 - 637
  • [33] NEURAL-NETWORK FOR THE EXACT RLS ADAPTIVE ALGORITHM
    LUO, FL
    LI, YD
    APPLIED MATHEMATICS AND COMPUTATION, 1994, 60 (2-3) : 103 - 111
  • [34] Neural-network algorithm for a graph layout problem
    Montana State Univ, Bozeman, United States
    IEEE Trans Neural Networks, 2 (341-345):
  • [35] A neural-network algorithm for a graph layout problem
    Cimikowski, R
    Shope, P
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (02): : 341 - 345
  • [36] Solving quasiparticle band spectra of real solids using neural-network quantum states
    Nobuyuki Yoshioka
    Wataru Mizukami
    Franco Nori
    Communications Physics, 4
  • [37] Role of stochastic noise and generalization error in the time propagation of neural-network quantum states
    Hofmann, Damian
    Fabiani, Giammarco
    Mentink, Johan H.
    Carleo, Giuseppe
    Sentef, Michael A.
    SCIPOST PHYSICS, 2022, 12 (05):
  • [38] ANALOG OPTIMIZATION WITH WONGS STOCHASTIC NEURAL-NETWORK
    KESIDIS, G
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (01): : 258 - 260
  • [39] OPTIMIZATION NEURAL-NETWORK FOR SOLVING FLOW PROBLEMS
    PERFETTI, R
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (05): : 1287 - 1291
  • [40] Solving quasiparticle band spectra of real solids using neural-network quantum states
    Yoshioka, Nobuyuki
    Mizukami, Wataru
    Nori, Franco
    COMMUNICATIONS PHYSICS, 2021, 4 (01)