{"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/sde-net-equipping-deep-neural-networks-with","title":"SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates","arxiv_id":"2008.10546","date":"2020-08-24","proceeding":"ICML 2020 1","authors":["Lingkai Kong","Jimeng Sun","Chao Zhang"],"abstract":"Uncertainty quantification is a fundamental yet unsolved problem for deep learning. The Bayesian framework provides a principled way of uncertainty estimation but is often not scalable to modern deep neural nets (DNNs) that have a large number of parameters. Non-Bayesian methods are simple to implement but often conflate different sources of uncertainties and require huge computing resources. We propose a new method for quantifying uncertainties of DNNs from a dynamical system perspective. The core of our method is to view DNN transformations as state evolution of a stochastic dynamical system and introduce a Brownian motion term for capturing epistemic uncertainty. Based on this perspective, we propose a neural stochastic differential equation model (SDE-Net) which consists of (1) a drift net that controls the system to fit the predictive function; and (2) a diffusion net that captures epistemic uncertainty. We theoretically analyze the existence and uniqueness of the solution to SDE-Net. Our experiments demonstrate that the SDE-Net model can outperform existing uncertainty estimation methods across a series of tasks where uncertainty plays a fundamental role.","url_abs":"https://arxiv.org/abs/2008.10546v1","url_pdf":"https://arxiv.org/pdf/2008.10546v1.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":"sde-net-equipping-deep-neural-networks-with","repo_url":"https://github.com/Lingkai-Kong/SDE-Net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sde-net-equipping-deep-neural-networks-with","repo_url":"https://github.com/Junghwan-brian/SDE-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2008.10546","atlas_url":"https://app.syntology.ai/?focus=2008.10546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.10546"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/Lingkai-Kong/SDE-Net","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Junghwan-brian/SDE-Net","reach":null}],"summary":{"ran_honours":5},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"80024dbc2d4746a2","entry":"dW","repo":"Junghwan-brian/SDE-Net","repo_kind":"listed","path":"euler_maruyama_simulation.py","file_url":"https://github.com/Junghwan-brian/SDE-Net/blob/HEAD/euler_maruyama_simulation.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"80024dbc2d4746a2"}},{"code_sha256_prefix":"79bd575f8de311d9","entry":"mse","repo":"Lingkai-Kong/SDE-Net","repo_kind":"official","path":"YearMSD/SDE_regression.py","file_url":"https://github.com/Lingkai-Kong/SDE-Net/blob/HEAD/YearMSD/SDE_regression.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"79bd575f8de311d9"}},{"code_sha256_prefix":"73c560f3f8fd01ed","entry":"mu","repo":"Junghwan-brian/SDE-Net","repo_kind":"listed","path":"euler_maruyama_simulation.py","file_url":"https://github.com/Junghwan-brian/SDE-Net/blob/HEAD/euler_maruyama_simulation.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"73c560f3f8fd01ed"}},{"code_sha256_prefix":"90e12c93d2ca890b","entry":"nll_loss","repo":"Lingkai-Kong/SDE-Net","repo_kind":"official","path":"YearMSD/SDE_regression.py","file_url":"https://github.com/Lingkai-Kong/SDE-Net/blob/HEAD/YearMSD/SDE_regression.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"90e12c93d2ca890b"}},{"code_sha256_prefix":"b69484de1f3d70dd","entry":"sigma","repo":"Junghwan-brian/SDE-Net","repo_kind":"listed","path":"euler_maruyama_simulation.py","file_url":"https://github.com/Junghwan-brian/SDE-Net/blob/HEAD/euler_maruyama_simulation.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b69484de1f3d70dd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}