{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7CZ3AWFYVHIEL734XYAFDQEO5B","short_pith_number":"pith:7CZ3AWFY","schema_version":"1.0","canonical_sha256":"f8b3b058b8a9d045ff7cbe0051c08ee84e012370b54f49aad3e0fddf96660278","source":{"kind":"arxiv","id":"1908.02718","version":1},"attestation_state":"computed","paper":{"title":"A Characterization of Mean Squared Error for Estimator with Bagging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Charles Dognin, Martin Mihelich, Michael Blot, Yan Shu","submitted_at":"2019-08-07T16:40:07Z","abstract_excerpt":"Bagging can significantly improve the generalization performance of unstable machine learning algorithms such as trees or neural networks. Though bagging is now widely used in practice and many empirical studies have explored its behavior, we still know little about the theoretical properties of bagged predictions. In this paper, we theoretically investigate how the bagging method can reduce the Mean Squared Error (MSE) when applied on a statistical estimator. First, we prove that for any estimator, increasing the number of bagged estimators $N$ in the average can only reduce the MSE. This int"},"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":"1908.02718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-07T16:40:07Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"232c16a27000d62981e8032358497cf9837dc928c1e166ebe4374e523320c2f9","abstract_canon_sha256":"388729d666815e620f5621bf82633f8c47d2fc3e43b864253578f39fbce01c5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:52:11.580927Z","signature_b64":"uRIgK5+t12SrmM77xfqPGZTvP8zCgpGj00rqL4QAr6DYxj6+IalRRpapxQuQy5eYcImiOZnqmlcxwBNVVKVyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8b3b058b8a9d045ff7cbe0051c08ee84e012370b54f49aad3e0fddf96660278","last_reissued_at":"2026-07-04T23:52:11.580502Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:52:11.580502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Characterization of Mean Squared Error for Estimator with Bagging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Charles Dognin, Martin Mihelich, Michael Blot, Yan Shu","submitted_at":"2019-08-07T16:40:07Z","abstract_excerpt":"Bagging can significantly improve the generalization performance of unstable machine learning algorithms such as trees or neural networks. Though bagging is now widely used in practice and many empirical studies have explored its behavior, we still know little about the theoretical properties of bagged predictions. In this paper, we theoretically investigate how the bagging method can reduce the Mean Squared Error (MSE) when applied on a statistical estimator. First, we prove that for any estimator, increasing the number of bagged estimators $N$ in the average can only reduce the MSE. This int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02718","kind":"arxiv","version":1},"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/1908.02718/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":"1908.02718","created_at":"2026-07-04T23:52:11.580574+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.02718v1","created_at":"2026-07-04T23:52:11.580574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02718","created_at":"2026-07-04T23:52:11.580574+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CZ3AWFYVHIE","created_at":"2026-07-04T23:52:11.580574+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CZ3AWFYVHIEL734","created_at":"2026-07-04T23:52:11.580574+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CZ3AWFY","created_at":"2026-07-04T23:52:11.580574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.02718","citing_title":"A Characterization of Mean Squared Error for Estimator with Bagging","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CZ3AWFYVHIEL734XYAFDQEO5B","json":"https://pith.science/pith/7CZ3AWFYVHIEL734XYAFDQEO5B.json","graph_json":"https://pith.science/api/pith-number/7CZ3AWFYVHIEL734XYAFDQEO5B/graph.json","events_json":"https://pith.science/api/pith-number/7CZ3AWFYVHIEL734XYAFDQEO5B/events.json","paper":"https://pith.science/paper/7CZ3AWFY"},"agent_actions":{"view_html":"https://pith.science/pith/7CZ3AWFYVHIEL734XYAFDQEO5B","download_json":"https://pith.science/pith/7CZ3AWFYVHIEL734XYAFDQEO5B.json","view_paper":"https://pith.science/paper/7CZ3AWFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.02718&json=true","fetch_graph":"https://pith.science/api/pith-number/7CZ3AWFYVHIEL734XYAFDQEO5B/graph.json","fetch_events":"https://pith.science/api/pith-number/7CZ3AWFYVHIEL734XYAFDQEO5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CZ3AWFYVHIEL734XYAFDQEO5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CZ3AWFYVHIEL734XYAFDQEO5B/action/storage_attestation","attest_author":"https://pith.science/pith/7CZ3AWFYVHIEL734XYAFDQEO5B/action/author_attestation","sign_citation":"https://pith.science/pith/7CZ3AWFYVHIEL734XYAFDQEO5B/action/citation_signature","submit_replication":"https://pith.science/pith/7CZ3AWFYVHIEL734XYAFDQEO5B/action/replication_record"}},"created_at":"2026-07-04T23:52:11.580574+00:00","updated_at":"2026-07-04T23:52:11.580574+00:00"}