{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/by-passing-the-kohn-sham-equations-with","title":"By-passing the Kohn-Sham equations with machine learning","arxiv_id":"1609.02815","date":"2016-09-09","proceeding":null,"authors":["Felix Brockherde","Leslie Vogt","Li Li","Mark E. Tuckerman","Kieron Burke","Klaus-Robert Müller"],"abstract":"Last year, at least 30,000 scientific papers used the Kohn-Sham scheme of\ndensity functional theory to solve electronic structure problems in a wide\nvariety of scientific fields, ranging from materials science to biochemistry to\nastrophysics. Machine learning holds the promise of learning the kinetic energy\nfunctional via examples, by-passing the need to solve the Kohn-Sham equations.\nThis should yield substantial savings in computer time, allowing either larger\nsystems or longer time-scales to be tackled, but attempts to machine-learn this\nfunctional have been limited by the need to find its derivative. The present\nwork overcomes this difficulty by directly learning the density-potential and\nenergy-density maps for test systems and various molecules. Both improved\naccuracy and lower computational cost with this method are demonstrated by\nreproducing DFT energies for a range of molecular geometries generated during\nmolecular dynamics simulations. Moreover, the methodology could be applied\ndirectly to quantum chemical calculations, allowing construction of density\nfunctionals of quantum-chemical accuracy.","url_abs":"http://arxiv.org/abs/1609.02815v3","url_pdf":"http://arxiv.org/pdf/1609.02815v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"by-passing-the-kohn-sham-equations-with","repo_url":"https://github.com/ccr-cheng/infgcn-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"by-passing-the-kohn-sham-equations-with","repo_url":"https://github.com/holywater2/GPWNO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"by-passing-the-kohn-sham-equations-with","repo_url":"https://github.com/seongsukim-ml/gpwno","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.02815","atlas_url":"https://app.syntology.ai/?focus=1609.02815","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}