Ab-initio solutions to the many-body Schödinger Equation with Deep Neural Networks

Variational approximations to the many-body Schrödinger equation can provide accurate energies and properties, but the accuracy is determined by the flexibility and representation capacity of the wavefunction form. We demonstrate that deep neural networks with physically-motivated structures offer a compact and highly accurate wavefunction Ansatz, can be efficiently optimized using variational Monte Carlo, and frequently outperform even diffusion Monte Carlo calculations using conventional wavefunctions. We demonstrate the applicability of our approach on a range of atoms, small molecules and model reactions.