Optimized Multifidelity Machine Learning for Quantum Chemistry
arXiv:2312.05661 · doi:10.1088/2632-2153/ad2cef
Abstract
Machine learning (ML) provides access to fast and accurate quantum chemistry (QC) calculations for various properties of interest such as excitation energies. It is often the case that high accuracy in prediction using an ML model, demands a large and costly training set. Various solutions and procedures have been presented to reduce this cost. These include methods such as -ML, hierarchical-ML, and multifidelity machine learning (MFML). MFML combines various -ML like sub-models for various fidelities according to a fixed scheme derived from the sparse grid combination technique. In this work we implement an optimization procedure to combine multifidelity models in a flexible scheme resulting in optimized MFML (o-MFML) that provides superior prediction capabilities. This hyper-parameter optimization is carried out on a holdout validation set of the property of interest. This work benchmarks the o-MFML method in predicting the atomization energies on the QM7b dataset, and again in the prediction of excitation energies for three molecules of growing size. The results indicate that o-MFML is a strong methodological improvement over MFML and provides lower error of prediction. Even in cases of poor data distributions and lack of clear hierarchies among the fidelities, which were previously identified as issues for multifidelity methods, the o-MFML provides advantage to the prediction of quantum chemical properties.
arXiv commentSI not included
References in corpus (25)
- Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
- On representing chemical environments
- Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
- SchNet - a deep learning architecture for molecules and materials
- ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
- Quantum-Chemical Insights from Deep Tensor Neural Networks
- Machine Learning of Accurate Energy-Conserving Molecular Force Fields
- PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
- Big Data meets Quantum Chemistry Approximations: The -Machine Learning Approach
- Comparing molecules and solids across structural and alchemical space
- Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
- Machine Learning of Molecular Electronic Properties in Chemical Compound Space
- Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
- Machine learning for electronically excited states of molecules
- FCHL revisited: faster and more accurate quantum machine learning
- Equivariant message passing for the prediction of tensorial properties and molecular spectra
- Finding unprecedentedly low-thermal-conductivity half-Heusler semiconductors via high-throughput materials modeling
- De novo exploration and self-guided learning of potential-energy surfaces
- Perspective on integrating machine learning into computational chemistry and materials science
- -Machine Learning for Potential Energy Surfaces: A PIP approach to bring a DFT-based PES to CCSD(T) Level of Theory
- Guest Editorial: Special Topic on Data-enabled Theoretical Chemistry
- Breaking the Coupled Cluster Barrier for Machine Learned Potentials of Large Molecules: The Case of 15-atom Acetylacetone
- Neural networks and kernel ridge regression for excited states dynamics of CHNH: From single-state to multi-state representations and multi-property machine learning models
- Automatically growing global reactive neural network potential energy surfaces: a trajectory free active learning strategy
- Multi-Fidelity Machine Learning for Excited State Energies of Molecules