Improved Optimization for the Neural-network Quantum States and Tests on the Chromium Dimer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917781028470784 |
|---|---|
| author | Li, Xiang Huang, Jia-Cheng Zhang, Guang-Ze Li, Hao-En Shen, Zhu-Ping Zhao, Chen Li, Jun Hu, Han-Shi |
| author_facet | Li, Xiang Huang, Jia-Cheng Zhang, Guang-Ze Li, Hao-En Shen, Zhu-Ping Zhao, Chen Li, Jun Hu, Han-Shi |
| contents | 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 $\rm H_2O$ and $\rm N_2$ within the cc-pVDZ basis set and calculate the ground-state energy of the strongly correlated chromium dimer ($\rm Cr_2$) 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 (RBM)-based NQS more effectively and marking a substantial advancement in NQS's practical quantum chemistry applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_09280 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improved Optimization for the Neural-network Quantum States and Tests on the Chromium Dimer Li, Xiang Huang, Jia-Cheng Zhang, Guang-Ze Li, Hao-En Shen, Zhu-Ping Zhao, Chen Li, Jun Hu, Han-Shi Chemical Physics Quantum Physics 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 $\rm H_2O$ and $\rm N_2$ within the cc-pVDZ basis set and calculate the ground-state energy of the strongly correlated chromium dimer ($\rm Cr_2$) 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 (RBM)-based NQS more effectively and marking a substantial advancement in NQS's practical quantum chemistry applications. |
| title | Improved Optimization for the Neural-network Quantum States and Tests on the Chromium Dimer |
| topic | Chemical Physics Quantum Physics |
| url | https://arxiv.org/abs/2404.09280 |