Learning DFT

Abstract

We present an extension of reverse engineered Kohn-Sham potentials from a density matrix renormalization group calculation towards the construction of a density functional theory functional via deep learning. Instead of applying machine learning to the energy functional itself, we apply these techniques to the Kohn-Sham potentials. To this end we develop a scheme to train a neural network to represent the mapping from local densities to Kohn-Sham potentials. Finally, we use the neural network to up-scale the simulation to larger system sizes.

11 page, 7 figures

References in corpus (5)

• Machine learning and the physical sciences
• New Trends in Density Matrix Renormalization
• Pure density functional for strong correlations and the thermodynamic limit from machine learning
• Exact ground state density functional theory for impurity models coupled to external reservoirs and transport calculations
• Inverse Mean Field Theory