Authors
Pescia, Gabriel; Han, Jiequn; Lovato, Alessandro; Lu, Jianfeng; Carleo, Giuseppe
Abstract
We introduce a family of neural quantum states for the simulation of strongly interacting systems in the presence of spatial periodicity. Our variational state is parameterized in terms of apermutationally-invariant part described by the Deep Sets neural-network architecture. The inputcoordinates to the Deep Sets are periodically transformed such that they are suitable to directlydescribe periodic bosonic systems. We show example applications to both one and two-dimensionalinteracting quantum gases with Gaussian interactions, as well as to 4He confined in a one-dimensionalgeometry. For the one-dimensional systems we find very precise estimations of the ground-state energies and the radial distribution functions of the particles. In two dimensions we obtain goodestimations of the ground-state energies, comparable to results obtained from more conventionalmethods.