Derivative Informed Learning of Exchange-Correlation Functionals

• URL: http://arxiv.org/abs/2606.04279v1
• Date: Tue, 02 Jun 2026 23:07:54 GMT
• Title: Derivative Informed Learning of Exchange-Correlation Functionals
• Abstract summary: Machine-learned (ML) exchange-correlation (XC) functionals aim to replace human-designed density functional approximations.<n>We study a hybrid-distillation setting in which $mathcalO(N4)$-scaling ML-XC functionals are trained to reproduce B3LYP/def2-SVP targets.<n>We introduce Derivative Informed XC-Loss (DI-Loss), a loss that incorporates additional information from the reference hybrid functional.
• Score: 46.44973075720396
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine-learned (ML) exchange-correlation (XC) functionals aim to replace human-designed density functional approximations by learning directly from reference data, but they still do not consistently outperform traditional $\mathcal{O}(N^4)$-scaling hybrid functionals. We study a hybrid-distillation setting in which $\mathcal{O}(N^3)$-scaling ML-XC functionals are trained to reproduce B3LYP/def2-SVP targets. We introduce Derivative Informed XC-Loss (DI-Loss), a loss that incorporates additional information from the reference hybrid functional by supervising first and second derivatives of the energy on the Grassmannian of admissible density matrices. Rather than only matching the self-consistent fixed point, DI-Loss aligns the local first- and second-order response of the learned functional with that of the target functional. Across four evaluated architectures, DI-Loss consistently improves the main energy metrics. Averaged uniformly across architectures, the total-energy MAE decreases by 66% relative to energy and density supervision alone. The density-sensitive mean-field energy metric $E_ρ$ improves from $1.2$ to $0.8$ mEh on average, while dipole and $\mathcal{L}_2$ density errors do not improve uniformly. We further show that densities from the distilled functionals reduce hybrid-functional SCF iterations by up to 50%. In downstream TDDFT calculations, Hessian supervision improves excited-state predictions, with XCdiff reducing the mean excitation-energy MAE by 19 - 35%.

Related papers

• A variational physics-informed graph neural network for heterogeneous solid mechanics [0.0]
  This work presents a variational, label-free physics-informed graph neural network (PI-GNN) in which the conforming is carried by the discretization rather than by the trial field.
  arXiv  Detail & Related papers  (2026-09-10T02:02:32Z)
• The Forgotten History of Wave Function Variance Optimization and its Relevance for Neural-Network VMC [0.0]
  Minimizing variance implicitly assumes a Gaussian local energy distribution.<n>For Coulombic systems, the local energy distribution exhibits $E-4$ power-law tails, causing the Central Limit Theorem to fail for the variance estimator.<n>We benchmark these functionals on $H+$, an exactly solvable system at every internuclear distance.<n>While energy minimization by construction yields the lowest energy, variance minimization is surpassed at every $R$ by alternative functionals.
  arXiv  Detail & Related papers  (2026-09-08T08:53:17Z)
• High-Probability Convergence in Decentralized Stochastic Optimization with Gradient Tracking [69.90407799170687]
  We study high-probability (HP) convergence guarantees in decentralized optimization.<n>Our results establish the same conditions on the horizon as in achieving comparable times.
  arXiv  Detail & Related papers  (2026-04-30T22:45:21Z)
• go-$m$HC: Direct Parameterization of Manifold-Constrained Hyper-Connections via Generalized Orthostochastic Matrices [0.0]
  We introduce a novel exact parameterization grounded in the theory of generalized orthostochastic matrices.<n>We instantiate this parameterization in go-$m$HC.<n>Our method composes naturally with Kronecker-factorized methods, substantially recovering expressivity at similar FLOP costs.
  arXiv  Detail & Related papers  (2026-04-02T17:51:19Z)
• Wiener Chaos Expansion based Neural Operator for Singular Stochastic Partial Differential Equations [58.188204772101756]
  This paper explores how our recently developed Wiener Chaos Expansion (WCE)-based neural operator (NO) can be applied to singular partial differential equations.<n>We leverage feature-wise linear modulation (FiLM) to appropriately capture the dependency between the solution of singular SPDE and its smooth remainder.<n>The resulting WCE-FiLM-NO shows excellent performance on $boldsymbol4$, as measured by relative $L$ loss, out-of-distribution and autocorrelation score.
  arXiv  Detail & Related papers  (2026-03-09T10:50:30Z)
• Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling [90.23688195918432]
  3D molecule generation is crucial for drug discovery and material science.<n>Existing approaches typically maintain separate latent spaces for invariant and equivariant modalities.<n>We propose textbfUAE-3D, a multi-modal VAE that compresses 3D molecules into latent sequences from a unified latent space.
  arXiv  Detail & Related papers  (2025-03-19T08:56:13Z)
• Learning Equivariant Non-Local Electron Density Functionals [51.721844709174206]
  We introduce Equivariant Graph Exchange Correlation (EG-XC), a novel non-local XC functional based on equivariant graph neural networks (GNNs)<n>By applying an equivariant GNN on this point cloud, we capture molecular-range interactions in a scalable and accurate manner.<n> EG-XC excels in data efficiency and molecular size extrapolation on QM9, matching force fields trained on 5 times more and larger molecules.
  arXiv  Detail & Related papers  (2024-10-10T14:31:45Z)
• eQE 2.0: Subsystem DFT Beyond GGA Functionals [58.720142291102135]
  subsystem-DFT (sDFT) can dramatically reduce the computational cost of large-scale electronic structure calculations. The key ingredients of sDFT are the nonadditive kinetic energy and exchange-correlation functionals which dominate it's accuracy. eQE 2.0 delivers excellent interaction energies compared to conventional Kohn-Sham DFT and CCSD(T)
  arXiv  Detail & Related papers  (2021-03-12T22:26:36Z)
• Too big, too small or just right? A benchmark assessment of density functional theory for predicting the spatial extent of the electron density of small chemical systems [0.0]
  A benchmark dataset of the prinicpal components of $mathcalK$ for 100 small molecules is developed. The performance of 47 popular and recent density functionals is assessed against this dataset.
  arXiv  Detail & Related papers  (2020-11-25T08:00:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.