Grad DFT: a software library for machine learning enhanced density functional theory

Abstract

Density functional theory (DFT) stands as a cornerstone method in computational quantum chemistry and materials science due to its remarkable versatility and scalability. Yet, it suffers from limitations in accuracy, particularly when dealing with strongly correlated systems. To address these shortcomings, recent work has begun to explore how machine learning can expand the capabilities of DFT; an endeavor with many open questions and technical challenges. In this work, we present Grad DFT: a fully differentiable JAX-based DFT library, enabling quick prototyping and experimentation with machine learning-enhanced exchange-correlation energy functionals. Grad DFT employs a pioneering parametrization of exchange-correlation functionals constructed using a weighted sum of energy densities, where the weights are determined using neural networks. Moreover, Grad DFT encompasses a comprehensive suite of auxiliary functions, notably featuring a just-in-time compilable and fully differentiable self-consistent iterative procedure. To support training and benchmarking efforts, we additionally compile a curated dataset of experimental dissociation energies of dimers, half of which contain transition metal atoms characterized by strong electronic correlations. The software library is tested against experimental results to study the generalization capabilities of a neural functional across potential energy surfaces and atomic species, as well as the effect of training data noise on the resulting model accuracy.

22 pages, 10 figures. The following article has been submitted to the Journal of Chemical Physics. After it is published, it will be found at https://publishing.aip.org/resources/librarians/products/journals/

References in corpus (10)

• Nonlocal van der Waals density functional: The simpler the better
• Libxc: a library of exchange and correlation functionals for density functional theory
• The discontinuous nature of the exchange-correlation functional -- critical for strongly correlated systems
• Machine learning and density functional theory
• Design and Analysis of Machine Learning Exchange-Correlation Functionals via Rotationally Invariant Convolutional Descriptors
• Predictive Power of the Exact Constraints and Appropriate Norms in Density Functional Theory
• Kohn-Sham theory with paramagnetic currents: compatibility and functional differentiability
• Efficient Learning of a One-dimensional Density Functional Theory
• What the foundations of quantum computer science teach us about chemistry
• D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory

Cited by in corpus (7)

• Performant Automatic Differentiation of Local Coupled Cluster Theories: Response Properties and Ab Initio Molecular Dynamics
• MOLPIPx: an end-to-end differentiable package for permutationally invariant polynomials in Python and Rust
• Learning Density Functionals from Noisy Quantum Data
• Leveraging Normalizing Flows for Orbital-Free Density Functional Theory
• Algorithmic differentiation for plane-wave DFT: materials design, error control and learning model parameters
• Neural network distillation of orbital dependent density functional theory
• Quantum-Enhanced Neural Exchange-Correlation Functionals