{"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/predictive-collective-variable-discovery-with","title":"Predictive Collective Variable Discovery with Deep Bayesian Models","arxiv_id":"1809.06913","date":"2018-09-18","proceeding":null,"authors":["Markus Schöberl","Nicholas Zabaras","Phaedon-Stelios Koutsourelakis"],"abstract":"Extending spatio-temporal scale limitations of models for complex atomistic\nsystems considered in biochemistry and materials science necessitates the\ndevelopment of enhanced sampling methods. The potential acceleration in\nexploring the configurational space by enhanced sampling methods depends on the\nchoice of collective variables (CVs). In this work, we formulate the discovery\nof CVs as a Bayesian inference problem and consider the CVs as hidden\ngenerators of the full-atomistic trajectory. The ability to generate samples of\nthe fine-scale atomistic configurations using limited training data allows us\nto compute estimates of observables as well as our probabilistic confidence on\nthem. The methodology is based on emerging methodological advances in machine\nlearning and variational inference. The discovered CVs are related to\nphysicochemical properties which are essential for understanding mechanisms\nespecially in unexplored complex systems. We provide a quantitative assessment\nof the CVs in terms of their predictive ability for alanine dipeptide (ALA-2)\nand ALA-15 peptide.","url_abs":"http://arxiv.org/abs/1809.06913v2","url_pdf":"http://arxiv.org/pdf/1809.06913v2.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":"predictive-collective-variable-discovery-with","repo_url":"https://github.com/cics-nd/predictive-cvs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.06913","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}