Convergence to the fixed-node limit in deep variational Monte Carlo
This work addresses the challenge of achieving high accuracy in electronic structure calculations for quantum chemistry, providing insights for improving neural network architectures in deep QMC, though it is incremental as it builds on existing deep QMC methods.
The paper tackled the convergence behavior of deep variational quantum Monte Carlo (QMC) ansatzes to the fixed-node limit, demonstrating that sufficiently large neural networks can achieve this limit and improve recovered correlation energy by half an order of magnitude compared to previous results.
Variational quantum Monte Carlo (QMC) is an ab-initio method for solving the electronic Schrödinger equation that is exact in principle, but limited by the flexibility of the available ansatzes in practice. The recently introduced deep QMC approach, specifically two deep-neural-network ansatzes PauliNet and FermiNet, allows variational QMC to reach the accuracy of diffusion QMC, but little is understood about the convergence behavior of such ansatzes. Here, we analyze how deep variational QMC approaches the fixed-node limit with increasing network size. First, we demonstrate that a deep neural network can overcome the limitations of a small basis set and reach the mean-field complete-basis-set limit. Moving to electron correlation, we then perform an extensive hyperparameter scan of a deep Jastrow factor for LiH and H$_4$ and find that variational energies at the fixed-node limit can be obtained with a sufficiently large network. Finally, we benchmark mean-field and many-body ansatzes on H$_2$O, increasing the fraction of recovered fixed-node correlation energy of single-determinant Slater--Jastrow-type ansatzes by half an order of magnitude compared to previous variational QMC results and demonstrate that a single-determinant Slater--Jastrow--backflow version of the ansatz overcomes the fixed-node limitations. This analysis helps understanding the superb accuracy of deep variational ansatzes in comparison to the traditional trial wavefunctions at the respective level of theory, and will guide future improvements of the neural network architectures in deep QMC.