Explicitly antisymmetrized neural network layers for variational Monte Carlo simulation
arXiv:2112.03491 · doi:10.1016/j.jcp.2022.111765
Abstract
The combination of neural networks and quantum Monte Carlo methods has arisen as a path forward for highly accurate electronic structure calculations. Previous proposals have combined equivariant neural network layers with an antisymmetric layer to satisfy the antisymmetry requirements of the electronic wavefunction. However, to date it is unclear if one can represent antisymmetric functions of physical interest, and it is difficult to measure the expressiveness of the antisymmetric layer. This work attempts to address this problem by introducing explicitly antisymmetrized universal neural network layers as a diagnostic tool. We first introduce a generic antisymmetric (GA) layer, which we use to replace the entire antisymmetric layer of the highly accurate ansatz known as the FermiNet. We demonstrate that the resulting FermiNet-GA architecture can yield effectively the exact ground state energy for small systems. We then consider a factorized antisymmetric (FA) layer which more directly generalizes the FermiNet by replacing products of determinants with products of antisymmetrized neural networks. Interestingly, the resulting FermiNet-FA architecture does not outperform the FermiNet. This suggests that the sum of products of antisymmetries is a key limiting aspect of the FermiNet architecture. To explore this further, we investigate a slight modification of the FermiNet called the full determinant mode, which replaces each product of determinants with a single combined determinant. The full single-determinant FermiNet closes a large part of the gap between the standard single-determinant FermiNet and FermiNet-GA. Surprisingly, on the nitrogen molecule at a dissociating bond length of 4.0 Bohr, the full single-determinant FermiNet can significantly outperform the standard 64-determinant FermiNet, yielding an energy within 0.4 kcal/mol of the best available computational benchmark.
arXiv comment33 pages, 14 figures
References in corpus (21)
- Solving the Quantum Many-Body Problem with Artificial Neural Networks
- Recent developments in the PySCF program package
- Deep neural network solution of the electronic Schrödinger equation
- Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
- Quantum Natural Gradient
- Why does deep and cheap learning work so well?
- Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
- Symmetries and many-body excited states with neural-network quantum states
- Fermionic neural-network states for ab-initio electronic structure
- Variational Quantum Monte Carlo Method with a Neural-Network Ansatz for Open Quantum Systems
- Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
- Energy and variance optimization of many body wave functions
- Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
- Optimizing large parameter sets in variational quantum Monte Carlo
- Role of backflow correlations for the non-magnetic phase of the t-t' Hubbard model
- Monte Carlo energy and variance minimization techniques for optimizing many-body wave functions
- Phases of two-dimensional spinless lattice fermions with first-quantized deep neural-network quantum states
- Deep Learning-Enhanced Variational Monte Carlo Method for Quantum Many-Body Physics
- Complementary First and Second Derivative Methods for Ansatz Optimization in Variational Monte Carlo
- Artificial Neural Networks as Trial Wave Functions for Quantum Monte Carlo
- An accelerated linear method for optimizing non-linear wavefunctions in variational Monte Carlo