English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Computing accurate yet efficient approximations to the solutions of theelectronic Schr\"odinger equation has been a paramount challenge ofcomputational chemistry for decades. Quantum Monte Carlo methods are apromising avenue of development as their core algorithm exhibits a number offavorable properties: it is highly parallel, and scales favorably with theconsidered system size, with an accuracy that is limited only by the choice ofthe wave function ansatz. The recently introduced machine-learnedparametrizations of quantum Monte Carlo ansatzes rely on the efficiency ofneural networks as universal function approximators to achieve state of the artaccuracy on a variety of molecular systems. With interest in the field growingrapidly, there is a clear need for easy to use, modular, and extendablesoftware libraries facilitating the development and adoption of this new classof methods. In this contribution, the DeepQMC program package is introduced, inan attempt to provide a common framework for future investigations by unifyingmany of the currently available deep-learning quantum Monte Carloarchitectures. Furthermore, the manuscript provides a brief introduction to themethodology of variational quantum Monte Carlo in real space, highlights sometechnical challenges of optimizing neural network wave functions, and presentsexample black-box applications of the program package. We thereby intend tomake this novel field accessible to a broader class of practitioners both fromthe quantum chemistry as well as the machine learning communities.

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