Abstract
Automatic differentiation represents a paradigm shift in scientific programming, where evaluating both functions and their derivatives is required for most applications. By removing the need to explicitly derive expressions for gradients, development times can be shortened and calculations can be simplified. For these reasons, automatic differentiation has fueled the rapid growth of a variety of sophisticated machine learning techniques over the past decade, but is now also increasingly showing its value to support ab initio simulations of quantum systems and enhance computational quantum chemistry. Here, we present an open-source differentiable quantum chemistry simulation code and explore applications facilitated by automatic differentiation: (1) calculating molecular perturbation properties, (2) reoptimizing a basis set for hydrocarbons, (3) checking the stability of self-consistent field wave functions, and (4) predicting molecular properties via alchemical perturbations.
Highlights
Automatic differentiation is a collection of techniques used to evaluate, up to machine precision, the derivative of a function specified by a computer program
To address the growing need for automatic differentiation in quantum chemistry, we introduce Differentiable Quantum Chemistry (DQC), a density functional theory (DFT) and Hartree–Fock (HF)15 simulation code
Quantum chemical calculations of the electronic structure typically require the evaluation of abstract functionals, such as root finding for self-consistent field (SCF) iterations, minimization for geometry optimizations, and the direct minimization approach to the SCF problem
Summary
Automatic differentiation is a collection of techniques used to evaluate, up to machine precision, the derivative of a function specified by a computer program. It allows software developers to focus solely on designing the best model for a given problem, without having to worry about implementing any derivatives of the model with respect to its various mathematical parameters It has already had a transformative effect in machine learning, enabling the development of many new techniques over the past decade, such as batch normalization, attention layers, and unique neural network architectures.. Automatic differentiation is an essential stepping stone to enable direct integration of quantum chemistry methods with machine learning models and their training In this context, a differentiable implementation of DFT was recently used to learn the xc functional from accurate reference calculations within the density matrix renormalization group approach or from a mixture of computational and experimental data, showing a promising new approach to developing transferable and robust xc functionals via deep learning
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
