Scaling Density Functional Theory with Gaussian Splatting
physics.chem-ph, cond-mat.mtrl-sci, cs.LG, physics.comp-ph
Submitted: 2026-09-25
Updated: 2026-09-25
Comments: 45 pages, 6 figures, 18 tables
Code: https://github.com/oogle/jax
License: http://creativecommons.org/licenses/by/4.0/
The gist: Density functional theory (DFT) strikes a practical balance between accuracy and computational cost in many problems of computational chemistry and materials science.
Terminology
Abstract
Density functional theory (DFT) strikes a practical balance between accuracy and computational cost in many problems of computational chemistry and materials science. However, many DFT calculations are limited by fixed atom-centered basis sets, which dictate how accuracy and cost scale with system size. We propose Gaussian Splatting for Density Functional Theory (GS-DFT), which represents molecular orbitals as a cloud of Gaussians whose positions, shapes, and mixing coefficients are optimized jointly by gradient descent to minimize the energy without training data. Conceptually, GS-DFT is 3D Gaussian splatting with the renderer replaced by quantum mechanics. We introduce two key solver components: adaptive density fitting with screening for efficient evaluation of two-electron integrals, and a regularized differentiable orthogonalization of the molecular orbitals. Empirically, the optimized basis reaches the accuracy of the largest conventional basis sets with a fraction of the parameters, converging systematically in energy, density, and nuclear forces. At equal parameter count, it captures the stretched-bond and anion physics that fixed bases only recover with specialized basis augmentation. The resulting solver exhibits quadratic peak memory scaling in the cloud size, allowing us to simulate systems of up to 2,742 atoms (10,406 electrons) without any modifications at triple-zeta scale using a single four-GPU node.
Sources
- MESS: Modern Electronic Structure Simulations
- Diagonalization without Diagonalization: A Direct Optimization Approach for Solid-State Density Functional Theory
- Multipole splats for optimized and inverted effective potentials
Related papers
- Solvating machine-learning interatomic potentials for solution-phase chemistry
- Transferable Generative Models Bridge Femtosecond to Nanosecond Time-Step Molecular Dynamics
- Accelerated "on-the-fly" coupled-cluster path-integral molecular dynamics: Impact of nuclear quantum effects on an asymmetric proton
- Learning Non-Local Molecular Interactions via Equivariant Local Representations and Charge Equilibration
- Variational Polaron Theory for Ground States of Strongly Coupled Light-Matter and Electron-Phonon Systems
- Pushing the accuracy of on-top functionals with agent-driven supervised learning