Finding Electronic Structure Machine Learning Surrogates without Training
- Center for Advanced Systems Understanding (CASUS), Görlitz (Germany); Helmholtz-Zentrum Dresden-Rossendorf (HZDR), (Germany); Technische Universität Dresden (Germany)
- Technische Universität Dresden (Germany)
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Center for Advanced Systems Understanding (CASUS), Görlitz (Germany); Helmholtz-Zentrum Dresden-Rossendorf (HZDR), (Germany)
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
A myriad of phenomena in materials science and chemistry rely on quantum-level simulations of the electronic structure in matter. While moving to larger length and time scales has been a pressing issue for decades, such large-scale electronic structure calculations are still challenging despite modern software approaches and advances in high-performance computing. The silver lining in this regard is the use of machine learning to accelerate electronic structure calculations – this line of research has recently gained growing attention. The grand challenge therein is finding a suitable machine-learning model during a process called hyperparameter optimization. This, however, causes a massive computational overhead in addition to that of data generation. We accelerate the construction of machine-learning surrogate models by roughly two orders of magnitude by circumventing excessive training during the hyperparameter optimization phase. We demonstrate our workflow for Kohn-Sham density functional theory, the most popular computational method in materials science and chemistry.
- Research Organization:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)
- DOE Contract Number:
- NA0003525
- OSTI ID:
- 1891948
- Report Number(s):
- SAND2022-14085R; 710828
- Country of Publication:
- United States
- Language:
- English
Similar Records
Surrogate Model Based Optimization for Finding Robust Deep Learning Model Architectures
An Integrated Software Package for Studying Structure-Property-Processing Relationships in Material Systems