Hyperparameter Optimization for Atomic Cluster Expansion Potentials
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914896069787648 |
|---|---|
| author | Toit, Daniel F. Thomas du Zhou, Yuxing Deringer, Volker L. |
| author_facet | Toit, Daniel F. Thomas du Zhou, Yuxing Deringer, Volker L. |
| contents | Machine-learning-based interatomic potentials enable accurate materials simulations on extended time- and lengthscales. ML potentials based on the Atomic Cluster Expansion (ACE) framework have recently shown promising performance for this purpose. Here, we describe a largely automated computational approach to optimizing hyperparameters for ACE potential models. We extend our openly available Python package, XPOT, to include an interface for ACE fitting, and discuss the optimization of the functional form and complexity of these models based on systematic sweeps across relevant hyperparameters. We showcase the usefulness of the approach for two example systems: the covalent network of silicon and the phase-change material Sb$_{2}$Te$_{3}$. More generally, our work emphasizes the importance of hyperparameter selection in the development of advanced ML potential models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00656 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hyperparameter Optimization for Atomic Cluster Expansion Potentials Toit, Daniel F. Thomas du Zhou, Yuxing Deringer, Volker L. Computational Physics Materials Science Machine-learning-based interatomic potentials enable accurate materials simulations on extended time- and lengthscales. ML potentials based on the Atomic Cluster Expansion (ACE) framework have recently shown promising performance for this purpose. Here, we describe a largely automated computational approach to optimizing hyperparameters for ACE potential models. We extend our openly available Python package, XPOT, to include an interface for ACE fitting, and discuss the optimization of the functional form and complexity of these models based on systematic sweeps across relevant hyperparameters. We showcase the usefulness of the approach for two example systems: the covalent network of silicon and the phase-change material Sb$_{2}$Te$_{3}$. More generally, our work emphasizes the importance of hyperparameter selection in the development of advanced ML potential models. |
| title | Hyperparameter Optimization for Atomic Cluster Expansion Potentials |
| topic | Computational Physics Materials Science |
| url | https://arxiv.org/abs/2408.00656 |