Training-free hyperparameter optimization of neural networks for electronic structures in matter

Abstract

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 neural network 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.

References in corpus (25)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Machine learning and the physical sciences
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• By-passing the Kohn-Sham equations with machine learning
• Machine-learning based interatomic potential for amorphous carbon
• Finding Density Functionals with Machine Learning
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• AiiDA 1.0, a scalable computational infrastructure for automated reproducible workflows and data provenance
• A neural network interatomic potential for the phase change material GeTe
• Local Spin-density Approximation Exchange-correlation Free-energy Functional
• Extending the Accuracy of the SNAP Interatomic Potential Form
• Ab initio Exchange-Correlation Free Energy of the Uniform Electron Gas at Warm Dense Matter Conditions
• Workflows in AiiDA: Engineering a high-throughput, event-based engine for robust and modular computational workflows
• Large scale and linear scaling DFT with the CONQUEST code
• Machine Learning the Physical Non-Local Exchange-Correlation Functional of Density-Functional Theory
• Quantum deep field: data-driven wave function, electron density generation, and atomization energy prediction and extrapolation with machine learning
• Explicit Multi-element Extension of the Spectral Neighbor Analysis Potential for Chemically Complex Systems
• Data-driven Material Models for Atomistic Simulation
• Accelerating Finite-temperature Kohn-Sham Density Functional Theory with Deep Neural Networks
• Exchange-correlation energy for the 3D homogeneous electron gas at arbitrary temperature
• Reconciling ionization energies and band gaps of warm dense matter derived with ab initio simulations and average atom models

Cited by in corpus (4)

• Electronic Density Response of Warm Dense Matter
• Predicting electronic structures at any length scale with machine learning
• Machine learning the electronic structure of matter across temperatures
• Physics-enhanced neural networks for equation-of-state calculations