{"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/a-large-scale-study-of-probabilistic","title":"A Large-Scale Study of Probabilistic Calibration in Neural Network Regression","arxiv_id":"2306.02738","date":"2023-06-05","proceeding":null,"authors":["Victor Dheur","Souhaib Ben Taieb"],"abstract":"Accurate probabilistic predictions are essential for optimal decision making. While neural network miscalibration has been studied primarily in classification, we investigate this in the less-explored domain of regression. We conduct the largest empirical study to date to assess the probabilistic calibration of neural networks. We also analyze the performance of recalibration, conformal, and regularization methods to enhance probabilistic calibration. Additionally, we introduce novel differentiable recalibration and regularization methods, uncovering new insights into their effectiveness. Our findings reveal that regularization methods offer a favorable tradeoff between calibration and sharpness. Post-hoc methods exhibit superior probabilistic calibration, which we attribute to the finite-sample coverage guarantee of conformal prediction. Furthermore, we demonstrate that quantile recalibration can be considered as a specific case of conformal prediction. Our study is fully reproducible and implemented in a common code base for fair comparisons.","url_abs":"https://arxiv.org/abs/2306.02738v2","url_pdf":"https://arxiv.org/pdf/2306.02738v2.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":"a-large-scale-study-of-probabilistic","repo_url":"https://github.com/vekteur/probabilistic-calibration-study","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"conformal-prediction","task_name":"Conformal Prediction"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.02738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02738"}},"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/vekteur/probabilistic-calibration-study","reach":null}],"summary":{"ran_draft_wrong":4,"ran_fixture":2,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":7,"samples":[{"code_sha256_prefix":"46b7d8f919823b56","entry":"compute_neg_entropy","repo":"vekteur/probabilistic-calibration-study","repo_kind":"official","path":"uq/models/regul/marginal_regul.py","file_url":"https://github.com/vekteur/probabilistic-calibration-study/blob/HEAD/uq/models/regul/marginal_regul.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"46b7d8f919823b56"}},{"code_sha256_prefix":"9e53f560b5b34b69","entry":"compute_neural_sort","repo":"vekteur/probabilistic-calibration-study","repo_kind":"official","path":"uq/models/regul/marginal_regul.py","file_url":"https://github.com/vekteur/probabilistic-calibration-study/blob/HEAD/uq/models/regul/marginal_regul.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"9e53f560b5b34b69"}},{"code_sha256_prefix":"c9f5b5643ef43ef6","entry":"map_tensor","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"c9f5b5643ef43ef6"}},{"code_sha256_prefix":"3ad2190d6dbacbfe","entry":"qr_loss","repo":"vekteur/probabilistic-calibration-study","repo_kind":"official","path":"uq/models/regul/marginal_regul.py","file_url":"https://github.com/vekteur/probabilistic-calibration-study/blob/HEAD/uq/models/regul/marginal_regul.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3ad2190d6dbacbfe"}},{"code_sha256_prefix":"5aafdd2507c47f3f","entry":"quantile_based_regul","repo":"vekteur/probabilistic-calibration-study","repo_kind":"official","path":"uq/models/regul/marginal_regul.py","file_url":"https://github.com/vekteur/probabilistic-calibration-study/blob/HEAD/uq/models/regul/marginal_regul.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"5aafdd2507c47f3f"}},{"code_sha256_prefix":"eac501ec140619f8","entry":"wrap_class","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"eac501ec140619f8"}},{"code_sha256_prefix":"58d68d33ad654bce","entry":"soft_sort","repo":"vekteur/probabilistic-calibration-study","repo_kind":"official","path":"uq/models/regul/marginal_regul.py","file_url":"https://github.com/vekteur/probabilistic-calibration-study/blob/HEAD/uq/models/regul/marginal_regul.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"58d68d33ad654bce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}