{"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/empirical-frequentist-coverage-of-deep-1","title":"Empirical Frequentist Coverage of Deep Learning Uncertainty Quantification Procedures","arxiv_id":"2010.03039","date":"2020-10-06","proceeding":null,"authors":["Benjamin Kompa","Jasper Snoek","Andrew Beam"],"abstract":"Uncertainty quantification for complex deep learning models is increasingly important as these techniques see growing use in high-stakes, real-world settings. Currently, the quality of a model's uncertainty is evaluated using point-prediction metrics such as negative log-likelihood or the Brier score on heldout data. In this study, we provide the first large scale evaluation of the empirical frequentist coverage properties of well known uncertainty quantification techniques on a suite of regression and classification tasks. We find that, in general, some methods do achieve desirable coverage properties on in distribution samples, but that coverage is not maintained on out-of-distribution data. Our results demonstrate the failings of current uncertainty quantification techniques as dataset shift increases and establish coverage as an important metric in developing models for real-world applications.","url_abs":"https://arxiv.org/abs/2010.03039v2","url_pdf":"https://arxiv.org/pdf/2010.03039v2.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":"empirical-frequentist-coverage-of-deep-1","repo_url":"https://github.com/beamlab-hsph/coverage_quantification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.03039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.03039"}},"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/beamlab-hsph/coverage_quantification","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"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":0,"samples":[{"code_sha256_prefix":"5f0acdff8e278043","entry":"compute_coverage","repo":"beamlab-hsph/coverage_quantification","repo_kind":"listed","path":"src/models/find_hyperparameters_non_svi_methods.py","file_url":"https://github.com/beamlab-hsph/coverage_quantification/blob/HEAD/src/models/find_hyperparameters_non_svi_methods.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5f0acdff8e278043"}},{"code_sha256_prefix":"4750678b384b6c5b","entry":"compute_quantiles","repo":"beamlab-hsph/coverage_quantification","repo_kind":"listed","path":"src/models/find_hyperparameters_non_svi_methods.py","file_url":"https://github.com/beamlab-hsph/coverage_quantification/blob/HEAD/src/models/find_hyperparameters_non_svi_methods.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4750678b384b6c5b"}},{"code_sha256_prefix":"454ea6fd1c88c8fd","entry":"get_data","repo":"beamlab-hsph/coverage_quantification","repo_kind":"listed","path":"src/models/data_utils.py","file_url":"https://github.com/beamlab-hsph/coverage_quantification/blob/HEAD/src/models/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"454ea6fd1c88c8fd"}},{"code_sha256_prefix":"98c106d55f5b9346","entry":"get_data_file_paths","repo":"beamlab-hsph/coverage_quantification","repo_kind":"listed","path":"src/models/data_utils.py","file_url":"https://github.com/beamlab-hsph/coverage_quantification/blob/HEAD/src/models/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"98c106d55f5b9346"}},{"code_sha256_prefix":"eafc9a17384a4762","entry":"get_index_train_test_path","repo":"beamlab-hsph/coverage_quantification","repo_kind":"listed","path":"src/models/data_utils.py","file_url":"https://github.com/beamlab-hsph/coverage_quantification/blob/HEAD/src/models/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eafc9a17384a4762"}},{"code_sha256_prefix":"7e25fbc2497a51bb","entry":"predict_N_times","repo":"beamlab-hsph/coverage_quantification","repo_kind":"listed","path":"src/models/find_hyperparameters_non_svi_methods.py","file_url":"https://github.com/beamlab-hsph/coverage_quantification/blob/HEAD/src/models/find_hyperparameters_non_svi_methods.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e25fbc2497a51bb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}