{"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/calibration-by-distribution-matching-1","title":"Calibration by Distribution Matching: Trainable Kernel Calibration Metrics","arxiv_id":"2310.20211","date":"2023-10-31","proceeding":"NeurIPS 2023 11","authors":["Charles Marx","Sofian Zalouk","Stefano Ermon"],"abstract":"Calibration ensures that probabilistic forecasts meaningfully capture uncertainty by requiring that predicted probabilities align with empirical frequencies. However, many existing calibration methods are specialized for post-hoc recalibration, which can worsen the sharpness of forecasts. Drawing on the insight that calibration can be viewed as a distribution matching task, we introduce kernel-based calibration metrics that unify and generalize popular forms of calibration for both classification and regression. These metrics admit differentiable sample estimates, making it easy to incorporate a calibration objective into empirical risk minimization. Furthermore, we provide intuitive mechanisms to tailor calibration metrics to a decision task, and enforce accurate loss estimation and no regret decisions. Our empirical evaluation demonstrates that employing these metrics as regularizers enhances calibration, sharpness, and decision-making across a range of regression and classification tasks, outperforming methods relying solely on post-hoc recalibration.","url_abs":"https://arxiv.org/abs/2310.20211v1","url_pdf":"https://arxiv.org/pdf/2310.20211v1.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":"calibration-by-distribution-matching-1","repo_url":"https://github.com/kernel-calibration/kernel-calibration","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.20211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.20211"}},"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/kernel-calibration/kernel-calibration","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":10,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":13,"ran":11,"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":"d8e925ee6db84c87","entry":"data_loader","repo":"kernel-calibration/kernel-calibration","repo_kind":"official","path":"torchuq/dataset/imagenet.py","file_url":"https://github.com/kernel-calibration/kernel-calibration/blob/HEAD/torchuq/dataset/imagenet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d8e925ee6db84c87"}},{"code_sha256_prefix":"9bc246bd29ace132","entry":"dirichlet_kernel","repo":"kernel-calibration/kernel-calibration","repo_kind":"official","path":"src/utils/ece_kde_utils.py","file_url":"https://github.com/kernel-calibration/kernel-calibration/blob/HEAD/src/utils/ece_kde_utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9bc246bd29ace132"}},{"code_sha256_prefix":"2f2e94d3c1dd5aa5","entry":"get_kernel","repo":"kernel-calibration/kernel-calibration","repo_kind":"official","path":"src/utils/ece_kde_utils.py","file_url":"https://github.com/kernel-calibration/kernel-calibration/blob/HEAD/src/utils/ece_kde_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f2e94d3c1dd5aa5"}},{"code_sha256_prefix":"4c0ab312755fbd43","entry":"gmm_cdf","repo":"kernel-calibration/kernel-calibration","repo_kind":"official","path":"src/utils/gmm_utils.py","file_url":"https://github.com/kernel-calibration/kernel-calibration/blob/HEAD/src/utils/gmm_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c0ab312755fbd43"}},{"code_sha256_prefix":"a99b14e0722ef72b","entry":"gmm_params_to_dist","repo":"kernel-calibration/kernel-calibration","repo_kind":"official","path":"src/utils/gmm_utils.py","file_url":"https://github.com/kernel-calibration/kernel-calibration/blob/HEAD/src/utils/gmm_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a99b14e0722ef72b"}},{"code_sha256_prefix":"fd941cc0cae06a27","entry":"loss_fn_1","repo":"kernel-calibration/kernel-calibration","repo_kind":"official","path":"src/metrics/decision_losses.py","file_url":"https://github.com/kernel-calibration/kernel-calibration/blob/HEAD/src/metrics/decision_losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd941cc0cae06a27"}},{"code_sha256_prefix":"42cdc115301b8340","entry":"mean_no_diag","repo":"kernel-calibration/kernel-calibration","repo_kind":"official","path":"src/metrics/losses.py","file_url":"https://github.com/kernel-calibration/kernel-calibration/blob/HEAD/src/metrics/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42cdc115301b8340"}},{"code_sha256_prefix":"cc30d0408372ef42","entry":"rbf_kernel","repo":"kernel-calibration/kernel-calibration","repo_kind":"official","path":"src/metrics/losses.py","file_url":"https://github.com/kernel-calibration/kernel-calibration/blob/HEAD/src/metrics/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc30d0408372ef42"}},{"code_sha256_prefix":"c2a7bb7f129c023a","entry":"tanh_kernel","repo":"kernel-calibration/kernel-calibration","repo_kind":"official","path":"src/metrics/losses.py","file_url":"https://github.com/kernel-calibration/kernel-calibration/blob/HEAD/src/metrics/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2a7bb7f129c023a"}},{"code_sha256_prefix":"d01f287e5bdb423e","entry":"train_dataset","repo":"kernel-calibration/kernel-calibration","repo_kind":"official","path":"torchuq/dataset/imagenet.py","file_url":"https://github.com/kernel-calibration/kernel-calibration/blob/HEAD/torchuq/dataset/imagenet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d01f287e5bdb423e"}},{"code_sha256_prefix":"4b7a8ee9ac4d3903","entry":"val_dataset","repo":"kernel-calibration/kernel-calibration","repo_kind":"official","path":"torchuq/dataset/imagenet.py","file_url":"https://github.com/kernel-calibration/kernel-calibration/blob/HEAD/torchuq/dataset/imagenet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b7a8ee9ac4d3903"}},{"code_sha256_prefix":"1229a437a6fcfedf","entry":"beta_kernel","repo":"kernel-calibration/kernel-calibration","repo_kind":"official","path":"src/utils/ece_kde_utils.py","file_url":"https://github.com/kernel-calibration/kernel-calibration/blob/HEAD/src/utils/ece_kde_utils.py","link_basis":"plan_row","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":"1229a437a6fcfedf"}},{"code_sha256_prefix":"81eeafdfab05075d","entry":"gmm_cdf_dist","repo":"kernel-calibration/kernel-calibration","repo_kind":"official","path":"src/utils/gmm_utils.py","file_url":"https://github.com/kernel-calibration/kernel-calibration/blob/HEAD/src/utils/gmm_utils.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":"81eeafdfab05075d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}