{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TNNL6MBLMB2QCIHF4ZWMH4GSY6","short_pith_number":"pith:TNNL6MBL","schema_version":"1.0","canonical_sha256":"9b5abf302b60750120e5e66cc3f0d2c7a296450d73bbbd8f761a20d5c314700c","source":{"kind":"arxiv","id":"1810.02453","version":1},"attestation_state":"computed","paper":{"title":"Correcting the bias in least squares regression with volume-rescaled sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Hsu, Manfred K. Warmuth, Micha{\\l} Derezi\\'nski","submitted_at":"2018-10-04T23:09:08Z","abstract_excerpt":"Consider linear regression where the examples are generated by an unknown distribution on $R^d\\times R$. Without any assumptions on the noise, the linear least squares solution for any i.i.d. sample will typically be biased w.r.t. the least squares optimum over the entire distribution. However, we show that if an i.i.d. sample of any size k is augmented by a certain small additional sample, then the solution of the combined sample becomes unbiased. We show this when the additional sample consists of d points drawn jointly according to the input distribution that is rescaled by the squared volu"},"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":"1810.02453","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-04T23:09:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fcba6cf79b22a5afc2db617ee0aab40d90bc8b8d736a0e35bfdb6f87653ac041","abstract_canon_sha256":"ae83103a8513d0e4d8cf2df5c9d031fe058ce472bf9a12ea7cd533a8d6e5dff2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:01.837696Z","signature_b64":"w+YS/bLHWpbdLnFZDlo+jrC+4APUcYgzOGaj6GmO0M67H0I17IbVzhbXL69oxmToEuSKlApJCTzKab5YdwHFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b5abf302b60750120e5e66cc3f0d2c7a296450d73bbbd8f761a20d5c314700c","last_reissued_at":"2026-05-18T00:04:01.837147Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:01.837147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Correcting the bias in least squares regression with volume-rescaled sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Hsu, Manfred K. Warmuth, Micha{\\l} Derezi\\'nski","submitted_at":"2018-10-04T23:09:08Z","abstract_excerpt":"Consider linear regression where the examples are generated by an unknown distribution on $R^d\\times R$. Without any assumptions on the noise, the linear least squares solution for any i.i.d. sample will typically be biased w.r.t. the least squares optimum over the entire distribution. However, we show that if an i.i.d. sample of any size k is augmented by a certain small additional sample, then the solution of the combined sample becomes unbiased. We show this when the additional sample consists of d points drawn jointly according to the input distribution that is rescaled by the squared volu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.02453","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":""},"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":"1810.02453","created_at":"2026-05-18T00:04:01.837230+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.02453v1","created_at":"2026-05-18T00:04:01.837230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.02453","created_at":"2026-05-18T00:04:01.837230+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNNL6MBLMB2Q","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNNL6MBLMB2QCIHF","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNNL6MBL","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNNL6MBLMB2QCIHF4ZWMH4GSY6","json":"https://pith.science/pith/TNNL6MBLMB2QCIHF4ZWMH4GSY6.json","graph_json":"https://pith.science/api/pith-number/TNNL6MBLMB2QCIHF4ZWMH4GSY6/graph.json","events_json":"https://pith.science/api/pith-number/TNNL6MBLMB2QCIHF4ZWMH4GSY6/events.json","paper":"https://pith.science/paper/TNNL6MBL"},"agent_actions":{"view_html":"https://pith.science/pith/TNNL6MBLMB2QCIHF4ZWMH4GSY6","download_json":"https://pith.science/pith/TNNL6MBLMB2QCIHF4ZWMH4GSY6.json","view_paper":"https://pith.science/paper/TNNL6MBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.02453&json=true","fetch_graph":"https://pith.science/api/pith-number/TNNL6MBLMB2QCIHF4ZWMH4GSY6/graph.json","fetch_events":"https://pith.science/api/pith-number/TNNL6MBLMB2QCIHF4ZWMH4GSY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNNL6MBLMB2QCIHF4ZWMH4GSY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNNL6MBLMB2QCIHF4ZWMH4GSY6/action/storage_attestation","attest_author":"https://pith.science/pith/TNNL6MBLMB2QCIHF4ZWMH4GSY6/action/author_attestation","sign_citation":"https://pith.science/pith/TNNL6MBLMB2QCIHF4ZWMH4GSY6/action/citation_signature","submit_replication":"https://pith.science/pith/TNNL6MBLMB2QCIHF4ZWMH4GSY6/action/replication_record"}},"created_at":"2026-05-18T00:04:01.837230+00:00","updated_at":"2026-05-18T00:04:01.837230+00:00"}