Variational principle to regularize machine-learned density functionals: the non-interacting kinetic-energy functional
This work addresses a key bottleneck in computational chemistry and materials science by improving the accuracy of density functional approximations, though it is incremental as it builds on existing machine-learning approaches.
The authors tackled the challenge of approximating the non-interacting kinetic-energy functional in density functional theory, which is crucial for accurate electronic structure calculations, by proposing a new regularization method for training deep neural network-based functionals, achieving excellent results on one-dimensional systems like hydrogen chains and atoms.
Practical density functional theory (DFT) owes its success to the groundbreaking work of Kohn and Sham that introduced the exact calculation of the non-interacting kinetic energy of the electrons using an auxiliary mean-field system. However, the full power of DFT will not be unleashed until the exact relationship between the electron density and the non-interacting kinetic energy is found. Various attempts have been made to approximate this functional, similar to the exchange--correlation functional, with much less success due to the larger contribution of kinetic energy and its more non-local nature. In this work we propose a new and efficient regularization method to train density functionals based on deep neural networks, with particular interest in the kinetic-energy functional. The method is tested on (effectively) one-dimensional systems, including the hydrogen chain, non-interacting electrons, and atoms of the first two periods, with excellent results. For the atomic systems, the generalizability of the regularization method is demonstrated by training also an exchange--correlation functional, and the contrasting nature of the two functionals is discussed from a machine-learning perspective.