Learning the exchange-correlation functional from nature with fully differentiable density functional theory

Abstract

Improving the predictive capability of molecular properties in ab initio simulations is essential for advanced material discovery. Despite recent progress making use of machine learning, utilizing deep neural networks to improve quantum chemistry modelling remains severely limited by the scarcity and heterogeneity of appropriate experimental data. Here we show how training a neural network to replace the exchange-correlation functional within a fully-differentiable three-dimensional Kohn-Sham density functional theory (DFT) framework can greatly improve simulation accuracy. Using only eight experimental data points on diatomic molecules, our trained exchange-correlation networks enable improved prediction accuracy of atomization energies across a collection of 104 molecules containing new bonds and atoms that are not present in the training dataset.

References in corpus (15)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Neural Message Passing for Quantum Chemistry
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• By-passing the Kohn-Sham equations with machine learning
• Machine learning prediction errors better than DFT accuracy
• Finding Density Functionals with Machine Learning
• Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
• DeePKS: a comprehensive data-driven approach towards chemically accurate density functional theory
• Automatic differentiation in quantum chemistry with an application to fully variational Hartree-Fock
• Design and Analysis of Machine Learning Exchange-Correlation Functionals via Rotationally Invariant Convolutional Descriptors
• Guided evolutionary strategies: Augmenting random search with surrogate gradients
• $\xi$-torch: differentiable scientific computing library
• Derivatives of partial eigendecomposition of a real symmetric matrix for degenerate cases

Cited by in corpus (29)

• DQC: a Python program package for Differentiable Quantum Chemistry
• Evolving symbolic density functionals
• Differentiable quantum chemistry with PySCF for molecules and materials at the mean-field level and beyond
• Machine Learning - Driven Materials Discovery: Unlocking Next-Generation Functional Materials - A review
• Learning Pair Potentials using Differentiable Simulations
• CIDER: An Expressive, Nonlocal Feature Set for Machine Learning Density Functionals with Exact Constraints
• Ligand additivity relationships enable efficient exploration of transition metal chemical space
• Automatic Differentiation for the Direct Minimization Approach to the Hartree-Fock Method
• Hybrid Classical/Machine-Learning Force Fields for the Accurate Description of Molecular Condensed-Phase Systems
• Nonlocal Machine-Learned Exchange Functional for Molecules and Solids
• Grad DFT: a software library for machine learning enhanced density functional theory
• Automatic Differentiation for Orbital-Free Density Functional Theory
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Inverse molecular design and parameter optimization with Hückel theory using automatic differentiation
• Variational principle to regularize machine-learned density functionals: the non-interacting kinetic-energy functional
• Addressing the Band Gap Problem with a Machine-Learned Exchange Functional
• Machine learning based nonlocal kinetic energy density functional for simple metals and alloys
• How Well Does Kohn-Sham Regularizer Work for Weakly Correlated Systems?
• Machine learning for accuracy in density functional approximations
• Accelerated free energy estimation in ab initio path integral Monte Carlo simulations
• Multi-channel machine learning based nonlocal kinetic energy density functional for semiconductors
• AD-NEGF: An End-to-End Differentiable Quantum Transport Simulator for Sensitivity Analysis and Inverse Problems
• Numerical stability and efficiency of response property calculations in density functional theory
• Machine learning-guided construction of an analytic kinetic energy functional for orbital free density functional theory
• MOLPIPx: an end-to-end differentiable package for permutationally invariant polynomials in Python and Rust
• Leveraging Normalizing Flows for Orbital-Free Density Functional Theory
• Algorithmic differentiation for plane-wave DFT: materials design, error control and learning model parameters
• Quantum-Enhanced Neural Exchange-Correlation Functionals
• Toward Density Functional Theory on Quantum Computers?