Stochastic gradient approximation method applied to Hubbard model

The two-dimensional Hubbard model is studied using the variational quantum Monte Carlo technique with Gutzwiller-type variational wave functions. In addition to the simple one-site correlated Gutzwiller wave function, we use a form with correlation between electrons on nearest- and next-nearest-neighbor sites. We show that the stochastic gradient approximation method suits very well for the optimization of the free parameters of the variational wave functions.