Message-Passing Neural Quantum States for the Homogeneous Electron Gas

Abstract

We introduce a message-passing-neural-network-based wave function Ansatz to simulate extended, strongly interacting fermions in continuous space. Symmetry constraints, such as continuous translation symmetries, can be readily embedded in the model. We demonstrate its accuracy by simulating the ground state of the homogeneous electron gas in three spatial dimensions at different densities and system sizes. With orders of magnitude fewer parameters than state-of-the-art neural-network wave functions, we demonstrate better or comparable ground-state energies. Reducing the parameter complexity allows scaling to $N=128$ electrons, previously inaccessible to neural-network wave functions in continuous space, enabling future work on finite-size extrapolations to the thermodynamic limit. We also show the Ansatz's capability of quantitatively representing different phases of matter.

13 pages, 5 figures

References in corpus (16)

• Inhomogeneous backflow transformations in quantum Monte Carlo calculations
• NetKet 3: Machine Learning Toolbox for Many-Body Quantum Systems
• Diffusion quantum Monte Carlo study of three-dimensional Wigner crystals
• Fermionic Wave Functions from Neural-Network Constrained Hidden States
• Discovering Quantum Phase Transitions with Fermionic Neural Networks
• Learning the ground state of a non-stoquastic quantum Hamiltonian in a rugged neural network landscape
• Ab initio calculation of real solids via neural network ansatz
• Wave function Ansatz (but Periodic) Networks and the Homogeneous Electron Gas
• Iterative backflow renormalization procedure for many-body ground state wave functions of strongly interacting normal Fermi liquids
• Towards efficient and accurate \emph{ab initio} solutions to periodic systems via transcorrelation and coupled cluster theory
• Nuclei with up to $\mathbf{A}=6$ nucleons with artificial neural network wave functions
• Low-density Phase Diagram of the Three-Dimensional Electron Gas
• Diffusion quantum Monte Carlo calculation of the quasiparticle effective mass of the two-dimensional homogeneous electron gas
• $m^{\ast }$ of two-dimensional electron gas: a neural canonical transformation study
• Jastrow correlation factor for periodic systems
• Correlation energy of the paramagnetic electron gas at the thermodynamic limit

Cited by in corpus (24)

• First principles simulations of dense hydrogen
• Accurate Computation of Quantum Excited States with Neural Networks
• Neural-network quantum states for many-body physics
• Ab-initio variational wave functions for the time-dependent many-electron Schrödinger equation
• Ground state phases of the two-dimension electron gas with a unified variational approach
• A Kaczmarz-inspired approach to accelerate the optimization of neural network wavefunctions
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Solving and visualizing fractional quantum Hall wavefunctions with neural network
• Exploring the design space of machine-learning models for quantum chemistry with a fully differentiable framework
• Is attention all you need to solve the correlated electron problem?
• Accurate neural quantum states for interacting lattice bosons
• Deep learning quantum Monte Carlo for solids
• Second-order optimisation strategies for neural network quantum states
• Spectroscopy of two-dimensional interacting lattice electrons using symmetry-aware neural backflow transformations
• Quantum Machine Learning of Molecular Energies with Hybrid Quantum-Neural Wavefunction
• Simple Fermionic backflow states via a systematically improvable tensor decomposition
• Phase diagram and crystal melting of helium-4 in two dimensions
• Physics-informed Transformers for Electronic Quantum States
• Determinant- and Derivative-Free Quantum Monte Carlo Within the Stochastic Representation of Wavefunctions
• Mott Transition and Volume Law Entanglement with Neural Quantum States
• Neural Wave Functions for High-Pressure Atomic Hydrogen
• Machine learning the single-$\Lambda$ hypernuclei with neural-network quantum states
• Expressivity of determinantal ansatzes for neural network wave functions
• A Denser Hydrogen Inferred from First-Principles Simulations Challenges Jupiter's Interior Models