{"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/experimental-study-of-neural-ode-training","title":"Experimental study of Neural ODE training with adaptive solver for dynamical systems modeling","arxiv_id":"2211.06972","date":"2022-11-13","proceeding":null,"authors":["Alexandre Allauzen","Thiago Petrilli Maffei Dardis","Hannah Plath"],"abstract":"Neural Ordinary Differential Equations (ODEs) was recently introduced as a new family of neural network models, which relies on black-box ODE solvers for inference and training. Some ODE solvers called adaptive can adapt their evaluation strategy depending on the complexity of the problem at hand, opening great perspectives in machine learning. However, this paper describes a simple set of experiments to show why adaptive solvers cannot be seamlessly leveraged as a black-box for dynamical systems modelling. By taking the Lorenz'63 system as a showcase, we show that a naive application of the Fehlberg's method does not yield the expected results. Moreover, a simple workaround is proposed that assumes a tighter interaction between the solver and the training strategy. The code is available on github: https://github.com/Allauzen/adaptive-step-size-neural-ode","url_abs":"https://arxiv.org/abs/2211.06972v1","url_pdf":"https://arxiv.org/pdf/2211.06972v1.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":"experimental-study-of-neural-ode-training","repo_url":"https://github.com/allauzen/adaptive-step-size-neural-ode","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.06972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.06972"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/allauzen/adaptive-step-size-neural-ode","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"df0bf345e65aa27f","entry":"ax_3D","repo":"allauzen/adaptive-step-size-neural-ode","repo_kind":"official","path":"fig_utils.py","file_url":"https://github.com/allauzen/adaptive-step-size-neural-ode/blob/HEAD/fig_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df0bf345e65aa27f"}},{"code_sha256_prefix":"da17cf8468c69888","entry":"euler_solve","repo":"allauzen/adaptive-step-size-neural-ode","repo_kind":"official","path":"ode_utils.py","file_url":"https://github.com/allauzen/adaptive-step-size-neural-ode/blob/HEAD/ode_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da17cf8468c69888"}},{"code_sha256_prefix":"50d6dd11295c4d19","entry":"euler_step","repo":"allauzen/adaptive-step-size-neural-ode","repo_kind":"official","path":"ode_utils.py","file_url":"https://github.com/allauzen/adaptive-step-size-neural-ode/blob/HEAD/ode_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50d6dd11295c4d19"}},{"code_sha256_prefix":"7ff4ce9985165bb1","entry":"ode_solve_2steps","repo":"allauzen/adaptive-step-size-neural-ode","repo_kind":"official","path":"ode_utils.py","file_url":"https://github.com/allauzen/adaptive-step-size-neural-ode/blob/HEAD/ode_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7ff4ce9985165bb1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}