DeepQMC: An open-source software suite for variational optimization of deep-learning molecular wave functions

Computing accurate yet efficient approximations to the solutions of the electronic Schr & ouml;dinger equation has been a paramount challenge of computational chemistry for decades. Quantum Monte Carlo methods are a promising avenue of development as their core algorithm exhibits a number of favorable properties: it is highly parallel and scales favorably with the considered system size, with an accuracy that is limited only by the choice of the wave function Ansatz. The recently introduced machine-learned parametrizations of quantum Monte Carlo Ans & auml;tze rely on the efficiency of neural networks as universal function approximators to achieve state of the art accuracy on a variety of molecular systems. With interest in the field growing rapidly, there is a clear need for easy to use, modular, and extendable software libraries facilitating the development and adoption of this new class of methods. In this contribution, the DEEPQMC program package is introduced, in an attempt to provide a common framework for future investigations by unifying many of the currently available deep-learning quantum Monte Carlo architectures. Furthermore, the manuscript provides a brief introduction to the methodology of variational quantum Monte Carlo in real space, highlights some technical challenges of optimizing neural network wave functions, and presents example black-box applications of the program package. We thereby intend to make this novel field accessible to a broader class of practitioners from both the quantum chemistry and the machine learning communities.

Automated summary

Computing accurate and efficient approximations to solve the Schrödinger equation in computational chemistry has been a challenge for decades. Quantum Monte Carlo methods, with their highly parallel and scalable algorithm, show promise in achieving high accuracy in a variety of molecular systems. The use of machine-learned parametrizations, relying on neural networks as universal function approximators, has further improved the accuracy of these methods. The development of software libraries like DEEPQMC aims to provide a common framework for future investigations and make this field accessible to practitioners from both the quantum chemistry and machine learning communities.