{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZFKTSK7Q5YEVVIK4ZPVRYYHYG5","short_pith_number":"pith:ZFKTSK7Q","schema_version":"1.0","canonical_sha256":"c955392bf0ee095aa15ccbeb1c60f8374de6f9523301febdf738de6ccf3c7a36","source":{"kind":"arxiv","id":"2202.04167","version":2},"attestation_state":"computed","paper":{"title":"Understanding the bias-variance tradeoff of Bregman divergences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Ben Adlam, Jamie Smith, Neha Gupta, Zelda Mariet","submitted_at":"2022-02-08T22:06:16Z","abstract_excerpt":"This paper builds upon the work of Pfau (2013), which generalized the bias variance tradeoff to any Bregman divergence loss function. Pfau (2013) showed that for Bregman divergences, the bias and variances are defined with respect to a central label, defined as the mean of the label variable, and a central prediction, of a more complex form. We show that, similarly to the label, the central prediction can be interpreted as the mean of a random variable, where the mean operates in a dual space defined by the loss function itself. Viewing the bias-variance tradeoff through operations taken in du"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2202.04167","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-02-08T22:06:16Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"92318498a093b617a18b93a46c3ee86871624b5f623008ecd4e6e3084690f9e3","abstract_canon_sha256":"67817b3c7c828aed930f9c0855c1409f9bd5c588289533eb351b88be4c6b3f3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:55:52.794520Z","signature_b64":"R+Yv1eHMkE2kKmFA8jty/bw1w6UjbkaQ1tlF7Rl3OfA9WeOMhLZZQRhi52lYU0qlNMZ/AfxBJmrnQG8ROH/zBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c955392bf0ee095aa15ccbeb1c60f8374de6f9523301febdf738de6ccf3c7a36","last_reissued_at":"2026-07-05T03:55:52.793937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:55:52.793937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the bias-variance tradeoff of Bregman divergences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Ben Adlam, Jamie Smith, Neha Gupta, Zelda Mariet","submitted_at":"2022-02-08T22:06:16Z","abstract_excerpt":"This paper builds upon the work of Pfau (2013), which generalized the bias variance tradeoff to any Bregman divergence loss function. Pfau (2013) showed that for Bregman divergences, the bias and variances are defined with respect to a central label, defined as the mean of the label variable, and a central prediction, of a more complex form. We show that, similarly to the label, the central prediction can be interpreted as the mean of a random variable, where the mean operates in a dual space defined by the loss function itself. Viewing the bias-variance tradeoff through operations taken in du"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.04167","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.04167/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2202.04167","created_at":"2026-07-05T03:55:52.794003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.04167v2","created_at":"2026-07-05T03:55:52.794003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.04167","created_at":"2026-07-05T03:55:52.794003+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFKTSK7Q5YEV","created_at":"2026-07-05T03:55:52.794003+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFKTSK7Q5YEVVIK4","created_at":"2026-07-05T03:55:52.794003+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFKTSK7Q","created_at":"2026-07-05T03:55:52.794003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17269","citing_title":"Calibeating for general proper losses: A Bregman divergence approach","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFKTSK7Q5YEVVIK4ZPVRYYHYG5","json":"https://pith.science/pith/ZFKTSK7Q5YEVVIK4ZPVRYYHYG5.json","graph_json":"https://pith.science/api/pith-number/ZFKTSK7Q5YEVVIK4ZPVRYYHYG5/graph.json","events_json":"https://pith.science/api/pith-number/ZFKTSK7Q5YEVVIK4ZPVRYYHYG5/events.json","paper":"https://pith.science/paper/ZFKTSK7Q"},"agent_actions":{"view_html":"https://pith.science/pith/ZFKTSK7Q5YEVVIK4ZPVRYYHYG5","download_json":"https://pith.science/pith/ZFKTSK7Q5YEVVIK4ZPVRYYHYG5.json","view_paper":"https://pith.science/paper/ZFKTSK7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.04167&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFKTSK7Q5YEVVIK4ZPVRYYHYG5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFKTSK7Q5YEVVIK4ZPVRYYHYG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFKTSK7Q5YEVVIK4ZPVRYYHYG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFKTSK7Q5YEVVIK4ZPVRYYHYG5/action/storage_attestation","attest_author":"https://pith.science/pith/ZFKTSK7Q5YEVVIK4ZPVRYYHYG5/action/author_attestation","sign_citation":"https://pith.science/pith/ZFKTSK7Q5YEVVIK4ZPVRYYHYG5/action/citation_signature","submit_replication":"https://pith.science/pith/ZFKTSK7Q5YEVVIK4ZPVRYYHYG5/action/replication_record"}},"created_at":"2026-07-05T03:55:52.794003+00:00","updated_at":"2026-07-05T03:55:52.794003+00:00"}