Neural network ansatz for periodic wave functions and the homogeneous electron gas
Max Wilson, Saverio Moroni, Markus Holzmann, Nicholas Gao, Filip Wudarski, Tejs Vegge, Arghya Bhowmik
Abstract
The authors introduce here WAPNET, a periodic neural network (NN) variational ansatz for solving the ground state of a homogeneous electron gas with high accuracy over a broad range of the density coupling constant ${r}_{s}$. Going beyond recent work for molecules, this contribution establishes NN models as flexible and powerful ansatz for electronic structure calculations in extended systems. In all density regimes, WAPNET-based variational Monte Carlo results are comparable to or better than state-of-the-art benchmarks obtained by diffusion Monte Carlo with iterative backflow.
Topics & Concepts
AnsatzHomogeneousElectronPhysicsWave functionArtificial neural networkMathematical physicsQuantum mechanicsStatistical physicsComputer scienceArtificial intelligenceQuantum chaos and dynamical systemsQuantum, superfluid, helium dynamicsQuantum Mechanics and Non-Hermitian Physics