Details

Autor(en) / Beteiligte

• Lee, Sebastian J. R.
• Husch, Tamara
• Ding, Feizhi
• Miller, Thomas F.

Titel

Analytical gradients for molecular-orbital-based machine learning

Ist Teil von

• The Journal of chemical physics, 2021-03, Vol.154 (12), p.124120-124120

Ort / Verlag

United States: American Institute of Physics

Erscheinungsjahr

2021

Quelle

American Institute of Physics

Beschreibungen/Notizen

• Molecular-orbital-based machine learning (MOB-ML) enables the prediction of accurate correlation energies at the cost of obtaining molecular orbitals. Here, we present the derivation, implementation, and numerical demonstration of MOB-ML analytical nuclear gradients, which are formulated in a general Lagrangian framework to enforce orthogonality, localization, and Brillouin constraints on the molecular orbitals. The MOB-ML gradient framework is general with respect to the regression technique (e.g., Gaussian process regression or neural networks) and the MOB feature design. We show that MOB-ML gradients are highly accurate compared to other ML methods on the ISO17 dataset while only being trained on energies for hundreds of molecules compared to energies and gradients for hundreds of thousands of molecules for the other ML methods. The MOB-ML gradients are also shown to yield accurate optimized structures at a computational cost for the gradient evaluation that is comparable to a density-corrected density functional theory calculation.