Neural network quantum statesãnalysis of the Shastry-Sutherland model

Abstract

We utilize neural network quantum states (NQS) to investigate the ground state properties of the Heisenberg model onã Shastry-Sutherland lattice using the variational Monte Carlo method. We show thatãlready relatively simple NQSs can be used toãpproximate the ground state of this model in its different phasesãnd regimes. We first compare several types of NQSs with each other on small latticesãnd benchmark their variational energiesãgainst the exact diagonalization results. Weãrgue that when precision, generality,ãnd computational costsãre taken intoãccount,ã good choice forãddressing larger systems isã shallow restricted Boltzmann machine NQS. We then show that such NQS can describe the main phases of the model in zero magnetic field. Moreover, NQS based onã restricted Boltzmann machine correctly describes the intriguing plateaus forming in magnetization of the modelãsã function of increasing magnetic field.