{"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/interpolated-adjoint-method-for-neural-odes","title":"Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs","arxiv_id":"2003.05271","date":"2020-03-11","proceeding":"NeurIPS 2020 12","authors":["Talgat Daulbaev","Alexandr Katrutsa","Larisa Markeeva","Julia Gusak","Andrzej Cichocki","Ivan Oseledets"],"abstract":"We propose a simple interpolation-based method for the efficient approximation of gradients in neural ODE models. We compare it with the reverse dynamic method (known in the literature as \"adjoint method\") to train neural ODEs on classification, density estimation, and inference approximation tasks. We also propose a theoretical justification of our approach using logarithmic norm formalism. As a result, our method allows faster model training than the reverse dynamic method that was confirmed and validated by extensive numerical experiments for several standard benchmarks.","url_abs":"https://arxiv.org/abs/2003.05271v2","url_pdf":"https://arxiv.org/pdf/2003.05271v2.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":"interpolated-adjoint-method-for-neural-odes","repo_url":"https://github.com/Daulbaev/IRDM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.05271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05271"}},"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/Daulbaev/IRDM","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":1,"unverified":2},"by_repo_kind":{"listed":{"samples":5,"ran":3,"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":"092979912309090a","entry":"get_normalization","repo":"Daulbaev/IRDM","repo_kind":"listed","path":"experiments/classification/train_cifar.py","file_url":"https://github.com/Daulbaev/IRDM/blob/HEAD/experiments/classification/train_cifar.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"092979912309090a"}},{"code_sha256_prefix":"a7a63b730e350c69","entry":"get_param_normalization","repo":"Daulbaev/IRDM","repo_kind":"listed","path":"experiments/classification/train_cifar.py","file_url":"https://github.com/Daulbaev/IRDM/blob/HEAD/experiments/classification/train_cifar.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a7a63b730e350c69"}},{"code_sha256_prefix":"f45990aee7c877a0","entry":"tol_scheduler","repo":"Daulbaev/IRDM","repo_kind":"listed","path":"experiments/classification/train_cifar.py","file_url":"https://github.com/Daulbaev/IRDM/blob/HEAD/experiments/classification/train_cifar.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":"f45990aee7c877a0"}},{"code_sha256_prefix":"33852494515c6a6f","entry":"odeint_chebyshev_func","repo":"Daulbaev/IRDM","repo_kind":"listed","path":"interpolated_torchdiffeq/_impl/odeint_interpolated.py","file_url":"https://github.com/Daulbaev/IRDM/blob/HEAD/interpolated_torchdiffeq/_impl/odeint_interpolated.py","link_basis":"first_harvest_node","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":"33852494515c6a6f"}},{"code_sha256_prefix":"53d5d8c7cd11168d","entry":"odeint_linear_func","repo":"Daulbaev/IRDM","repo_kind":"listed","path":"interpolated_torchdiffeq/_impl/odeint_interpolated.py","file_url":"https://github.com/Daulbaev/IRDM/blob/HEAD/interpolated_torchdiffeq/_impl/odeint_interpolated.py","link_basis":"first_harvest_node","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":"53d5d8c7cd11168d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}