Self-consistency error correction for accurate machine learning potentials from variational Monte Carlo
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911254989242368 |
|---|---|
| author | Tenti, Giacomo Nakano, Kousuke Casula, Michele |
| author_facet | Tenti, Giacomo Nakano, Kousuke Casula, Michele |
| contents | Variational Monte Carlo (VMC) can be used to train accurate machine learning interatomic potentials (MLIPs), enabling molecular dynamics (MD) simulations of complex materials on time scales and for system sizes previously unattainable. VMC training sets are often based on partially optimized wave functions (WFs) to circumvent expensive energy optimizations of the whole set of WF parameters. However, frozen variational parameters lead to VMC forces and pressures not consistent with the underlying potential energy surface, a bias called the self-consistency error (SCE). Here, we demonstrate how the SCE can spoil the accuracy of MLIPs trained on these data, taking high-pressure hydrogen as test case. We then apply a recently introduced SCE correction [ Phys. Rev. B 109, 205151 (2024)] to generate unbiased VMC training sets based on a Jastrow-correlated single determinant WF with frozen Kohn-Sham orbitals. The MLIPs generated within this framework are significantly improved and can approach in quality those trained on datasets built with fully optimized WFs. Our conclusions are further supported by MD simulations, which show how MLIPs trained on SCE-corrected datasets systematically yield more reliable physical observables. Our framework opens the possibility of constructing extended high-quality training sets with VMC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20481 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-consistency error correction for accurate machine learning potentials from variational Monte Carlo Tenti, Giacomo Nakano, Kousuke Casula, Michele Strongly Correlated Electrons Disordered Systems and Neural Networks Materials Science Variational Monte Carlo (VMC) can be used to train accurate machine learning interatomic potentials (MLIPs), enabling molecular dynamics (MD) simulations of complex materials on time scales and for system sizes previously unattainable. VMC training sets are often based on partially optimized wave functions (WFs) to circumvent expensive energy optimizations of the whole set of WF parameters. However, frozen variational parameters lead to VMC forces and pressures not consistent with the underlying potential energy surface, a bias called the self-consistency error (SCE). Here, we demonstrate how the SCE can spoil the accuracy of MLIPs trained on these data, taking high-pressure hydrogen as test case. We then apply a recently introduced SCE correction [ Phys. Rev. B 109, 205151 (2024)] to generate unbiased VMC training sets based on a Jastrow-correlated single determinant WF with frozen Kohn-Sham orbitals. The MLIPs generated within this framework are significantly improved and can approach in quality those trained on datasets built with fully optimized WFs. Our conclusions are further supported by MD simulations, which show how MLIPs trained on SCE-corrected datasets systematically yield more reliable physical observables. Our framework opens the possibility of constructing extended high-quality training sets with VMC. |
| title | Self-consistency error correction for accurate machine learning potentials from variational Monte Carlo |
| topic | Strongly Correlated Electrons Disordered Systems and Neural Networks Materials Science |
| url | https://arxiv.org/abs/2504.20481 |