{"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/reliable-training-and-estimation-of-variance","title":"Reliable training and estimation of variance networks","arxiv_id":"1906.03260","date":"2019-06-04","proceeding":"NeurIPS 2019 12","authors":["Nicki S. Detlefsen","Martin Jørgensen","Søren Hauberg"],"abstract":"We propose and investigate new complementary methodologies for estimating predictive variance networks in regression neural networks. We derive a locally aware mini-batching scheme that result in sparse robust gradients, and show how to make unbiased weight updates to a variance network. Further, we formulate a heuristic for robustly fitting both the mean and variance networks post hoc. Finally, we take inspiration from posterior Gaussian processes and propose a network architecture with similar extrapolation properties to Gaussian processes. The proposed methodologies are complementary, and improve upon baseline methods individually. Experimentally, we investigate the impact on predictive uncertainty on multiple datasets and tasks ranging from regression, active learning and generative modeling. Experiments consistently show significant improvements in predictive uncertainty estimation over state-of-the-art methods across tasks and datasets.","url_abs":"https://arxiv.org/abs/1906.03260v2","url_pdf":"https://arxiv.org/pdf/1906.03260v2.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":"reliable-training-and-estimation-of-variance","repo_url":"https://github.com/SkafteNicki/john","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"reliable-training-and-estimation-of-variance","repo_url":"https://github.com/astirn/variational-variance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1906.03260","atlas_url":"https://app.syntology.ai/?focus=1906.03260","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.03260"}},"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/SkafteNicki/john","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/astirn/variational-variance","reach":null}],"summary":{"ran_draft_wrong":7,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1},"listed":{"samples":6,"ran":5,"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":4,"samples":[{"code_sha256_prefix":"88e013a94fe15c9f","entry":"drop_detlefsen","repo":"astirn/variational-variance","repo_kind":"listed","path":"regression_analysis.py","file_url":"https://github.com/astirn/variational-variance/blob/HEAD/regression_analysis.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":"88e013a94fe15c9f"}},{"code_sha256_prefix":"1212679baefb9b71","entry":"gen_Qw","repo":"SkafteNicki/john","repo_kind":"official","path":"locality_sampler.py","file_url":"https://github.com/SkafteNicki/john/blob/HEAD/locality_sampler.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1212679baefb9b71"}},{"code_sha256_prefix":"93b3ea16c3cdd175","entry":"integrate_active_learning_curves","repo":"astirn/variational-variance","repo_kind":"listed","path":"active_learning_analysis.py","file_url":"https://github.com/astirn/variational-variance/blob/HEAD/active_learning_analysis.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":"93b3ea16c3cdd175"}},{"code_sha256_prefix":"6170c011a2239b60","entry":"keep_fashion","repo":"astirn/variational-variance","repo_kind":"listed","path":"generative_analysis.py","file_url":"https://github.com/astirn/variational-variance/blob/HEAD/generative_analysis.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":"6170c011a2239b60"}},{"code_sha256_prefix":"f6fa0ca68d2fe1e2","entry":"keep_mnist","repo":"astirn/variational-variance","repo_kind":"listed","path":"generative_analysis.py","file_url":"https://github.com/astirn/variational-variance/blob/HEAD/generative_analysis.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":"f6fa0ca68d2fe1e2"}},{"code_sha256_prefix":"142eaf6178104a3f","entry":"locality_sampler","repo":"SkafteNicki/john","repo_kind":"official","path":"locality_sampler.py","file_url":"https://github.com/SkafteNicki/john/blob/HEAD/locality_sampler.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"142eaf6178104a3f"}},{"code_sha256_prefix":"6cafd798a1a01685","entry":"locality_sampler2","repo":"SkafteNicki/john","repo_kind":"official","path":"locality_sampler.py","file_url":"https://github.com/SkafteNicki/john/blob/HEAD/locality_sampler.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6cafd798a1a01685"}},{"code_sha256_prefix":"2a8e9acf7f3436c8","entry":"string_table","repo":"astirn/variational-variance","repo_kind":"listed","path":"generative_analysis.py","file_url":"https://github.com/astirn/variational-variance/blob/HEAD/generative_analysis.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":"2a8e9acf7f3436c8"}},{"code_sha256_prefix":"c858f668b539babc","entry":"gp","repo":"SkafteNicki/john","repo_kind":"official","path":"experiment_active_learning.py","file_url":"https://github.com/SkafteNicki/john/blob/HEAD/experiment_active_learning.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c858f668b539babc"}},{"code_sha256_prefix":"818d4dd7e1be914f","entry":"uci_reported","repo":"astirn/variational-variance","repo_kind":"listed","path":"regression_analysis.py","file_url":"https://github.com/astirn/variational-variance/blob/HEAD/regression_analysis.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":"818d4dd7e1be914f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}