南方科技大学知识苑(SUSTech KC): Improved optimization for the neural-network quantum states and tests on the chromium dimer

题名	Improved optimization for the neural-network quantum states and tests on the chromium dimer
作者	Li，Xiang 1; Huang，Jia Cheng 1; Zhang，Guang Ze 1; Li，Hao En 1; Shen，Zhu Ping 1; Zhao，Chen 1; Li，Jun1,2,3 ; Hu，Han Shi 1
通讯作者	Li，Xiang
发表日期	2024-06-21
DOI	10.1063/5.0214150
发表期刊	Journal of Chemical Physics 影响因子和分区
ISSN	0021-9606
EISSN	1089-7690
卷号	160 期号:23
摘要	The advent of Neural-network Quantum States (NQS) has significantly advanced wave function ansatz research, sparking a resurgence in orbital space variational Monte Carlo (VMC) exploration. This work introduces three algorithmic enhancements to reduce computational demands of VMC optimization using NQS: an adaptive learning rate algorithm, constrained optimization, and block optimization. We evaluate the refined algorithm on complex multireference bond stretches of HO and N within the cc-pVDZ basis set and calculate the ground-state energy of the strongly correlated chromium dimer (Cr) in the Ahlrichs SV basis set. Our results achieve superior accuracy compared to coupled cluster theory at a relatively modest CPU cost. This work demonstrates how to enhance optimization efficiency and robustness using these strategies, opening a new path to optimize large-scale restricted Boltzmann machine-based NQS more effectively and marking a substantial advancement in NQS’s practical quantum chemistry applications.
相关链接	[Scopus记录]
收录类别	SCI ; EI
语种	英语
学校署名	其他
ESI学科分类	CHEMISTRY
Scopus记录号	2-s2.0-85196436696
来源库	Scopus
引用统计	被引频次[WOS]：1
成果类型	期刊论文
条目标识符	http://sustech.caswiz.com/handle/2SGJ60CL/778681
专题	理学院_化学系
作者单位	1.Department of Chemistry and Engineering Research,Center of Advanced Rare-Earth Materials,Ministry of Education,Tsinghua University,Beijing,100084,China 2.Department of Chemistry,Guangdong Provincial Key Laboratory of Catalytic Chemistry,Southern University of Science and Technology,Shenzhen,518055,China 3.Fundamental Science Center of Rare Earths,Ganjiang Innovation Academy,Chinese Academy of Sciences,Ganzhou,341000,China
推荐引用方式 GB/T 7714	Li，Xiang,Huang，Jia Cheng,Zhang，Guang Ze,et al. Improved optimization for the neural-network quantum states and tests on the chromium dimer[J]. Journal of Chemical Physics,2024,160(23).
APA	Li，Xiang.,Huang，Jia Cheng.,Zhang，Guang Ze.,Li，Hao En.,Shen，Zhu Ping.,...&Hu，Han Shi.(2024).Improved optimization for the neural-network quantum states and tests on the chromium dimer.Journal of Chemical Physics,160(23).
MLA	Li，Xiang,et al."Improved optimization for the neural-network quantum states and tests on the chromium dimer".Journal of Chemical Physics 160.23(2024).