Large Electron Model: A Universal Ground State Predictor

TL;DR

The paper presents Large Electron Model, a neural network that accurately predicts ground state wavefunctions of interacting electrons across various parameters, enabling efficient material discovery and surpassing traditional density functional theory.

Contribution

Introduces a universal neural network model with Fermi Sets architecture for predicting many-electron ground states across parameter spaces.

Findings

Accurately predicts wavefunctions for up to 50 electrons.

Generalizes across unseen coupling strengths and particle sectors.

Provides accurate charge densities and energies.

Abstract

We introduce Large Electron Model, a single neural network model that produces variational wavefunctions of interacting electrons over the entire Hamiltonian parameter manifold. Our model employs the Fermi Sets architecture, a universal representation of many-body fermionic wavefunctions, which is further conditioned on Hamiltonian parameter and particle number. On interacting electrons in a two-dimensional harmonic potential, a single trained model accurately predicts the ground state wavefunction while generalizing across unseen coupling strengths and particle-number sectors, producing both accurate real-space charge densities and ground state energies, even up to $50$ particles. Our results establish a foundation model method for material discovery that is grounded in the variational principle, while accurately treating strong electron correlation beyond the capacity of density functional theory.