Electronic excited states from physically constrained machine learning

E Cignoni, D Suman, J Nigam, L Cupellini… - ACS Central …, 2024 - ACS Publications
Data-driven techniques are increasingly used to replace electronic-structure calculations of
matter. In this context, a relevant question is whether machine learning (ML) should be …

Neural-network density functional theory based on variational energy minimization

Y Li, Z Tang, Z Chen, M Sun, B Zhao, H Li, H Tao… - Physical Review Letters, 2024 - APS
Deep-learning density functional theory (DFT) shows great promise to significantly
accelerate material discovery and potentially revolutionize materials research. However …

Equivariance via minimal frame averaging for more symmetries and efficiency

Y Lin, J Helwig, S Gui, S Ji - arxiv preprint arxiv:2406.07598, 2024 - arxiv.org
We consider achieving equivariance in machine learning systems via frame averaging.
Current frame averaging methods involve a costly sum over large frames or rely on sampling …

A space group symmetry informed network for o (3) equivariant crystal tensor prediction

K Yan, A Saxton, X Qian, X Qian, S Ji - arxiv preprint arxiv:2406.12888, 2024 - arxiv.org
We consider the prediction of general tensor properties of crystalline materials, including
dielectric, piezoelectric, and elastic tensors. A key challenge here is how to make the …

Self-consistency training for density-functional-theory hamiltonian prediction

H Zhang, C Liu, Z Wang, X Wei, S Liu, N Zheng… - arxiv preprint arxiv …, 2024 - arxiv.org
Predicting the mean-field Hamiltonian matrix in density functional theory is a fundamental
formulation to leverage machine learning for solving molecular science problems. Yet, its …