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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Finding accurate solutions to the Schr\"odinger equation is the key unsolvedchallenge of computational chemistry. Given its importance for the developmentof new chemical compounds, decades of research have been dedicated to thisproblem, but due to the large dimensionality even the best available methods donot yet reach the desired accuracy. Recently the combination of deep learningwith Monte Carlo methods has emerged as a promising way to obtain highlyaccurate energies and moderate scaling of computational cost. In this paper wesignificantly contribute towards this goal by introducing a novel deep-learningarchitecture that achieves 40-70% lower energy error at 6x lower computationalcost compared to previous approaches. Using our method we establish a newbenchmark by calculating the most accurate variational ground state energiesever published for a number of different atoms and molecules. We systematicallybreak down and measure our improvements, focusing in particular on the effectof increasing physical prior knowledge. We surprisingly find that increasingthe prior knowledge given to the architecture can actually decrease accuracy.

Gold-standard solutions to the Schr\"odinger equation using deep learning: How much physics do we need?