{"type":"preprint","language":[{"iso":"eng"}],"user_id":"85279","related_material":{"link":[{"url":"https://github.com/Christian-Offen/Lagrangian_GP","relation":"software","description":"GitHub"}]},"publication_status":"submitted","ddc":["510"],"title":"Machine learning of continuous and discrete variational ODEs with convergence guarantee and uncertainty quantification","year":"2024","date_created":"2024-04-30T16:04:40Z","date_updated":"2024-05-01T04:42:25Z","status":"public","_id":"53805","file_date_updated":"2024-04-30T16:02:21Z","abstract":[{"text":"The article introduces a method to learn dynamical systems that are governed by Euler--Lagrange equations from data.\r\nThe method is based on Gaussian process regression and identifies continuous or discrete Lagrangians and is, therefore, structure preserving by design.\r\nA rigorous proof of convergence as the distance between observation data points converges to zero is provided.\r\nNext to convergence guarantees, the method allows for quantification of model uncertainty, which can provide a basis of adaptive sampling techniques. We provide efficient uncertainty quantification of any observable that is linear in the Lagrangian, including of Hamiltonian functions (energy) and symplectic structures, which is of interest in the context of system identification.\r\nThe article overcomes major practical and theoretical difficulties related to the ill-posedness of the identification task of (discrete) Lagrangians through a careful design of geometric regularisation strategies and through an exploit of a relation to convex minimisation problems in reproducing kernel Hilbert spaces.","lang":"eng"}],"file":[{"access_level":"open_access","creator":"coffen","title":"Machine learning of continuous and discrete variational ODEs with convergence guarantee and uncertainty quantification","file_name":"L_Collocation_ODE.pdf","description":"Preprint of article","content_type":"application/pdf","file_id":"53806","date_updated":"2024-04-30T16:02:21Z","relation":"main_file","file_size":1681917,"date_created":"2024-04-30T16:02:21Z"}],"department":[{"_id":"636"}],"oa":"1","has_accepted_license":"1","author":[{"full_name":"Offen, Christian","last_name":"Offen","first_name":"Christian","id":"85279","orcid":"0000-0002-5940-8057"}],"external_id":{"arxiv":["arXiv:2404.19626"]},"citation":{"ieee":"C. Offen, “Machine learning of continuous and discrete variational ODEs with convergence guarantee and uncertainty quantification.” .","chicago":"Offen, Christian. “Machine Learning of Continuous and Discrete Variational ODEs with Convergence Guarantee and Uncertainty Quantification,” n.d.","apa":"Offen, C. (n.d.). <i>Machine learning of continuous and discrete variational ODEs with convergence guarantee and uncertainty quantification</i>.","short":"C. Offen, (n.d.).","ama":"Offen C. Machine learning of continuous and discrete variational ODEs with convergence guarantee and uncertainty quantification.","bibtex":"@article{Offen, title={Machine learning of continuous and discrete variational ODEs with convergence guarantee and uncertainty quantification}, author={Offen, Christian} }","mla":"Offen, Christian. <i>Machine Learning of Continuous and Discrete Variational ODEs with Convergence Guarantee and Uncertainty Quantification</i>."}}