Improving the performance of fermionic neural networks with the Slater
In this work, we propose a technique for the use of fermionic neural
networks (FermiNets) with the Slater exponential Ansatz for
electron-nuclear and electron-electron distances, which provides faster
convergence of target ground-state energies due to a better description
of the interparticle interaction in the vicinities of the coalescence
points. Our analysis of learning curves indicates on the possibility to
obtain accurate energies with smaller batch sizes using arguments of the
bagging approach. In order to obtain even more accurate results for the
ground-state energies, we propose an extrapolation scheme for estimating
Monte Carlo integrals in the limit of an infinite number of points.
Numerical tests for a set of molecules demonstrate a good agreement with
the results of the original FermiNets approach (achieved with larger
batch sizes than required by our approach) and with results of the
coupled-cluster singles and doubles with perturbative triples (CCSD(T))
method that are calculated in the complete basis set (CBS) limit.