Agnostic calculation of atomic free energies with the descriptor density of states
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_ | 1866910858589765632 |
|---|---|
| author | Swinburne, Thomas D Lapointe, Clovis Marinica, Mihai-Cosmin |
| author_facet | Swinburne, Thomas D Lapointe, Clovis Marinica, Mihai-Cosmin |
| contents | We present a new method to evaluate vibrational free energies of atomic systems without a priori specification of an interatomic potential. Our model-agnostic approach leverages descriptors, high-dimensional feature vectors of atomic structure. The entropy of a high-dimensional density, the descriptor density of states, is accurately estimated with conditional score matching. Casting interatomic potentials into a form extensive in descriptor features, we show free energies emerge as the Legendre-Fenchel conjugate of the descriptor entropy, avoiding all high-dimensional integration. The score matching campaign requires less resources than fixed-model sampling and is highly parallel, reducing wall time to a few minutes, with tensor compression schemes allowing lightweight storage. Our model-agnostic estimator returns differentiable free energy predictions over a broad range of potential parameters in microseconds of CPU effort, allowing rapid forward and back propagation of potential variations through finite temperature simulations, long desired for uncertainty quantification and inverse design. We test predictions against thermodynamic integration calculations over a broad range of models for BCC, FCC and A15 phases of W, Mo and Fe at high homologous temperatures. Predictions pass the stringent accuracy threshold of 1-2 meV/atom (1/40-1/20 kcal/mol) for phase prediction with propagated score uncertainties robustly bounding errors. We also demonstrate targeted fine-tuning, reducing the alpha-gamma transition temperature in a non-magnetic machine learning model of Fe from 2030 K to 1063 K through back-propagation, with no additional sampling. Applications to liquids and fine-tuning foundational models are discussed along with the many problems in computational science which estimate high-dimensional integrals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_18191 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Agnostic calculation of atomic free energies with the descriptor density of states Swinburne, Thomas D Lapointe, Clovis Marinica, Mihai-Cosmin Materials Science Statistical Mechanics We present a new method to evaluate vibrational free energies of atomic systems without a priori specification of an interatomic potential. Our model-agnostic approach leverages descriptors, high-dimensional feature vectors of atomic structure. The entropy of a high-dimensional density, the descriptor density of states, is accurately estimated with conditional score matching. Casting interatomic potentials into a form extensive in descriptor features, we show free energies emerge as the Legendre-Fenchel conjugate of the descriptor entropy, avoiding all high-dimensional integration. The score matching campaign requires less resources than fixed-model sampling and is highly parallel, reducing wall time to a few minutes, with tensor compression schemes allowing lightweight storage. Our model-agnostic estimator returns differentiable free energy predictions over a broad range of potential parameters in microseconds of CPU effort, allowing rapid forward and back propagation of potential variations through finite temperature simulations, long desired for uncertainty quantification and inverse design. We test predictions against thermodynamic integration calculations over a broad range of models for BCC, FCC and A15 phases of W, Mo and Fe at high homologous temperatures. Predictions pass the stringent accuracy threshold of 1-2 meV/atom (1/40-1/20 kcal/mol) for phase prediction with propagated score uncertainties robustly bounding errors. We also demonstrate targeted fine-tuning, reducing the alpha-gamma transition temperature in a non-magnetic machine learning model of Fe from 2030 K to 1063 K through back-propagation, with no additional sampling. Applications to liquids and fine-tuning foundational models are discussed along with the many problems in computational science which estimate high-dimensional integrals. |
| title | Agnostic calculation of atomic free energies with the descriptor density of states |
| topic | Materials Science Statistical Mechanics |
| url | https://arxiv.org/abs/2502.18191 |