Adaptive hybrid density functionals
Danish Khan, Alastair James Arthur Price, Maximilian L. Ach, and O., Anatole von Lilienfeld

TL;DR
This paper introduces an adaptive hybrid density functional, aPBE0, which dynamically adjusts the exact exchange ratio for any chemical compound using data-efficient quantum machine learning, significantly improving accuracy in quantum chemistry calculations.
Contribution
The paper presents a novel adaptive hybrid density functional that optimizes exchange contributions on the fly with machine learning, enhancing accuracy over traditional fixed-parameter functionals.
Findings
aPBE0 improves atomization energy accuracy and cures the spin gap problem.
Enhanced energetics, electron densities, and HOMO-LUMO gaps in organic molecules.
Revision of QM9 dataset (revQM9) with superior quality metrics.
Abstract
Exact exchange contributions are known to crucially affect electronic states, which in turn govern covalent bond formation and breaking in chemical species. Empirically averaging the exact exchange admixture over compositional degrees of freedom, hybrid density functional approximations have been widely successful, yet have fallen short to reach high level quantum chemistry accuracy, primarily due to delocalization errors. We propose to `adaptify` hybrid functionals by generating optimal admixture ratios of exact exchange on the fly, i.e. specifically for any chemical compound, using extremely data efficient quantum machine learning models that carry negligible overhead. The adaptive Perdew-Burke-Ernzerhof based hybrid density functional (aPBE0) is shown to yield atomization energies with sufficient accuracy to effectively cure the infamous spin gap problem in open shell systems, such…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning in Materials Science · Catalysis and Oxidation Reactions · History and advancements in chemistry
