{"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/implicit-regularization-of-deep-residual","title":"Implicit regularization of deep residual networks towards neural ODEs","arxiv_id":"2309.01213","date":"2023-09-03","proceeding":null,"authors":["Pierre Marion","Yu-Han Wu","Michael E. Sander","Gérard Biau"],"abstract":"Residual neural networks are state-of-the-art deep learning models. Their continuous-depth analog, neural ordinary differential equations (ODEs), are also widely used. Despite their success, the link between the discrete and continuous models still lacks a solid mathematical foundation. In this article, we take a step in this direction by establishing an implicit regularization of deep residual networks towards neural ODEs, for nonlinear networks trained with gradient flow. We prove that if the network is initialized as a discretization of a neural ODE, then such a discretization holds throughout training. Our results are valid for a finite training time, and also as the training time tends to infinity provided that the network satisfies a Polyak-Lojasiewicz condition. Importantly, this condition holds for a family of residual networks where the residuals are two-layer perceptrons with an overparameterization in width that is only linear, and implies the convergence of gradient flow to a global minimum. Numerical experiments illustrate our results.","url_abs":"https://arxiv.org/abs/2309.01213v3","url_pdf":"https://arxiv.org/pdf/2309.01213v3.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":"implicit-regularization-of-deep-residual","repo_url":"https://github.com/michaelsdr/implicit-regularization-resnets-nodes","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2309.01213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01213"}},"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/michaelsdr/implicit-regularization-resnets-nodes","reach":null}],"summary":{"ran_honours":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"9e75157a4fa4aa8b","entry":"loss","repo":"michaelsdr/implicit-regularization-resnets-nodes","repo_kind":"official","path":"finite_training_time_convergence.py","file_url":"https://github.com/michaelsdr/implicit-regularization-resnets-nodes/blob/HEAD/finite_training_time_convergence.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e75157a4fa4aa8b"}},{"code_sha256_prefix":"5c9c60032bf7c292","entry":"loss","repo":"michaelsdr/implicit-regularization-resnets-nodes","repo_kind":"official","path":"infinite_training_time.py","file_url":"https://github.com/michaelsdr/implicit-regularization-resnets-nodes/blob/HEAD/infinite_training_time.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c9c60032bf7c292"}},{"code_sha256_prefix":"5c4fb8ae9ff35f14","entry":"make_data","repo":"michaelsdr/implicit-regularization-resnets-nodes","repo_kind":"official","path":"finite_training_time_convergence.py","file_url":"https://github.com/michaelsdr/implicit-regularization-resnets-nodes/blob/HEAD/finite_training_time_convergence.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c4fb8ae9ff35f14"}},{"code_sha256_prefix":"9938cf775b5e2a1e","entry":"make_data","repo":"michaelsdr/implicit-regularization-resnets-nodes","repo_kind":"official","path":"infinite_training_time.py","file_url":"https://github.com/michaelsdr/implicit-regularization-resnets-nodes/blob/HEAD/infinite_training_time.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9938cf775b5e2a1e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}