Automatic Differentiation for Orbital-Free Density Functional Theory

Abstract

Differentiable programming has facilitated numerous methodological advances in scientific computing. Physics engines supporting automatic differentiation have simpler code, accelerating the development process and reducing the maintenance burden. Furthermore, fully-differentiable simulation tools enable direct evaluation of challenging derivatives - including those directly related to properties measurable by experiment - that are conventionally computed with finite difference methods. Here, we investigate automatic differentiation in the context of orbital-free density functional theory (OFDFT) simulations of materials, introducing PROFESS-AD. Its automatic evaluation of properties derived from first derivatives, including functional potentials, forces, and stresses, facilitates the development and testing of new density functionals, while its direct evaluation of properties requiring higher-order derivatives, such as bulk moduli, elastic constants, and force constants, offers more concise implementations compared to conventional finite difference methods. For these reasons, PROFESS-AD serves as an excellent prototyping tool and provides new opportunities for OFDFT.

References in corpus (10)

• TorchMD: A deep learning framework for molecular simulations
• Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
• Learning the exchange-correlation functional from nature with fully differentiable density functional theory
• TiC lattice dynamics from ab initio calculations
• DQC: a Python program package for Differentiable Quantum Chemistry
• Data-driven kinetic energy density fitting for orbital-free DFT: linear vs Gaussian process regression
• Jellium-with-gap model applied to semilocal kinetic functionals
• Order-$N$ orbital-free density-functional calculations with machine learning of functional derivatives for semiconductors and metals
• How Well Does Kohn-Sham Regularizer Work for Weakly Correlated Systems?
• Real space pairwise electrostatic summation in a uniform neutralising background

Cited by in corpus (7)

• Exploring the design space of machine-learning models for quantum chemistry with a fully differentiable framework
• Machine learning for accuracy in density functional approximations
• 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
• Solving deep-learning density functional theory via variational autoencoders
• eminus -- Pythonic electronic structure theory