{"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/scalable-gradients-for-stochastic","title":"Scalable Gradients for Stochastic Differential Equations","arxiv_id":"2001.01328","date":"2020-01-05","proceeding":null,"authors":["Xuechen Li","Ting-Kam Leonard Wong","Ricky T. Q. Chen","David Duvenaud"],"abstract":"The adjoint sensitivity method scalably computes gradients of solutions to ordinary differential equations. We generalize this method to stochastic differential equations, allowing time-efficient and constant-memory computation of gradients with high-order adaptive solvers. Specifically, we derive a stochastic differential equation whose solution is the gradient, a memory-efficient algorithm for caching noise, and conditions under which numerical solutions converge. In addition, we combine our method with gradient-based stochastic variational inference for latent stochastic differential equations. We use our method to fit stochastic dynamics defined by neural networks, achieving competitive performance on a 50-dimensional motion capture dataset.","url_abs":"https://arxiv.org/abs/2001.01328v6","url_pdf":"https://arxiv.org/pdf/2001.01328v6.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":"scalable-gradients-for-stochastic","repo_url":"https://github.com/google-research/torchsde","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"scalable-gradients-for-stochastic","repo_url":"https://github.com/JFagin/latent_SDE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"scalable-gradients-for-stochastic","repo_url":"https://github.com/xwinxu/bayesde","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"scalable-gradients-for-stochastic","repo_url":"https://github.com/xwinxu/bayesian-sde","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"sensitivity","task_name":"Sensitivity"},{"task_slug":"variational-inference","task_name":"Variational Inference"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"exponential-decay","method_name":"Exponential Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-prediction-on-cmu-mocap-2","task":"Video Prediction","dataset":"CMU Mocap-2","model":"Latent SDE","rank_in_archive_order":1,"of":4,"metrics":{"Test Error":"4.03"},"uses_additional_data":false},{"leaderboard":"/sota/video-prediction-on-cmu-mocap-2","task":"Video Prediction","dataset":"CMU Mocap-2","model":"Latent ODE","rank_in_archive_order":2,"of":4,"metrics":{"Test Error":"5.98"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2001.01328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.01328"}},"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/google-research/torchsde","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xwinxu/bayesde","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JFagin/latent_SDE","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xwinxu/bayesian-sde","reach":null}],"summary":{"ran_violates":1,"unverified":4},"by_repo_kind":{"listed":{"samples":3,"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":2,"samples":[{"code_sha256_prefix":"6a904c09f82ab220","entry":"str2bool","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"6a904c09f82ab220"}},{"code_sha256_prefix":"ff96c7be4662524f","entry":"evaluate_loss","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ff96c7be4662524f"}},{"code_sha256_prefix":"d82ed5ed65c58a23","entry":"sdeint_ito","repo":"xwinxu/bayesde","repo_kind":"listed","path":"jaxsde/jaxsde/sdeint.py","file_url":"https://github.com/xwinxu/bayesde/blob/HEAD/jaxsde/jaxsde/sdeint.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":"d82ed5ed65c58a23"}},{"code_sha256_prefix":"c67ae22fcae712b7","entry":"sdeint_ito_fixed_grid","repo":"xwinxu/bayesde","repo_kind":"listed","path":"jaxsde/jaxsde/sdeint.py","file_url":"https://github.com/xwinxu/bayesde/blob/HEAD/jaxsde/jaxsde/sdeint.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":"c67ae22fcae712b7"}},{"code_sha256_prefix":"dd6e88e990764ff3","entry":"sdeint_strat","repo":"xwinxu/bayesde","repo_kind":"listed","path":"jaxsde/jaxsde/sdeint.py","file_url":"https://github.com/xwinxu/bayesde/blob/HEAD/jaxsde/jaxsde/sdeint.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":"dd6e88e990764ff3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}