{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AQRCLLEDUOHH3RBWSGP25M67GP","short_pith_number":"pith:AQRCLLED","schema_version":"1.0","canonical_sha256":"042225ac83a38e7dc436919faeb3df33cd41742fab7573e35c51ec8cb432ab96","source":{"kind":"arxiv","id":"1806.06761","version":2},"attestation_state":"computed","paper":{"title":"Optimal Subsampling Algorithms for Big Data Regressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.CO","stat.TH"],"primary_cat":"stat.ME","authors_text":"Haiying Wang, Huiming Zhang, Jun Yu, Mingyao Ai","submitted_at":"2018-06-18T15:15:41Z","abstract_excerpt":"To fast approximate maximum likelihood estimators with massive data, this paper studies the Optimal Subsampling Method under the A-optimality Criterion (OSMAC) for generalized linear models. The consistency and asymptotic normality of the estimator from a general subsampling algorithm are established, and optimal subsampling probabilities under the A- and L-optimality criteria are derived. Furthermore, using Frobenius norm matrix concentration inequalities, finite sample properties of the subsample estimator based on optimal subsampling probabilities are also derived. Since the optimal subsamp"},"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":"1806.06761","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2018-06-18T15:15:41Z","cross_cats_sorted":["math.ST","stat.CO","stat.TH"],"title_canon_sha256":"2eade0287efc26efe7191805d6f0c29fb457e3b52eb71e083c4d68a633cbe347","abstract_canon_sha256":"0ae4c7569319d64ad2e6a6add4fb76ed4c5c12bc041e9aac3f12169d76b9314a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:31.233917Z","signature_b64":"6grecD832M9mN7/PLznuWTROFYBsFr+pbJiAD3ll7LgJYC227Fh/rSsCPFRgBhlLPsK9UcUKelfcTrbIqW3CBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"042225ac83a38e7dc436919faeb3df33cd41742fab7573e35c51ec8cb432ab96","last_reissued_at":"2026-07-05T02:48:31.233435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:31.233435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Subsampling Algorithms for Big Data Regressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.CO","stat.TH"],"primary_cat":"stat.ME","authors_text":"Haiying Wang, Huiming Zhang, Jun Yu, Mingyao Ai","submitted_at":"2018-06-18T15:15:41Z","abstract_excerpt":"To fast approximate maximum likelihood estimators with massive data, this paper studies the Optimal Subsampling Method under the A-optimality Criterion (OSMAC) for generalized linear models. The consistency and asymptotic normality of the estimator from a general subsampling algorithm are established, and optimal subsampling probabilities under the A- and L-optimality criteria are derived. Furthermore, using Frobenius norm matrix concentration inequalities, finite sample properties of the subsample estimator based on optimal subsampling probabilities are also derived. Since the optimal subsamp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06761","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/1806.06761/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":"1806.06761","created_at":"2026-07-05T02:48:31.233496+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.06761v2","created_at":"2026-07-05T02:48:31.233496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06761","created_at":"2026-07-05T02:48:31.233496+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQRCLLEDUOHH","created_at":"2026-07-05T02:48:31.233496+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQRCLLEDUOHH3RBW","created_at":"2026-07-05T02:48:31.233496+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQRCLLED","created_at":"2026-07-05T02:48:31.233496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11738","citing_title":"Renewable Lasso without Batch-Number Constraints: A Gradient-Enhanced Approach","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQRCLLEDUOHH3RBWSGP25M67GP","json":"https://pith.science/pith/AQRCLLEDUOHH3RBWSGP25M67GP.json","graph_json":"https://pith.science/api/pith-number/AQRCLLEDUOHH3RBWSGP25M67GP/graph.json","events_json":"https://pith.science/api/pith-number/AQRCLLEDUOHH3RBWSGP25M67GP/events.json","paper":"https://pith.science/paper/AQRCLLED"},"agent_actions":{"view_html":"https://pith.science/pith/AQRCLLEDUOHH3RBWSGP25M67GP","download_json":"https://pith.science/pith/AQRCLLEDUOHH3RBWSGP25M67GP.json","view_paper":"https://pith.science/paper/AQRCLLED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.06761&json=true","fetch_graph":"https://pith.science/api/pith-number/AQRCLLEDUOHH3RBWSGP25M67GP/graph.json","fetch_events":"https://pith.science/api/pith-number/AQRCLLEDUOHH3RBWSGP25M67GP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQRCLLEDUOHH3RBWSGP25M67GP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQRCLLEDUOHH3RBWSGP25M67GP/action/storage_attestation","attest_author":"https://pith.science/pith/AQRCLLEDUOHH3RBWSGP25M67GP/action/author_attestation","sign_citation":"https://pith.science/pith/AQRCLLEDUOHH3RBWSGP25M67GP/action/citation_signature","submit_replication":"https://pith.science/pith/AQRCLLEDUOHH3RBWSGP25M67GP/action/replication_record"}},"created_at":"2026-07-05T02:48:31.233496+00:00","updated_at":"2026-07-05T02:48:31.233496+00:00"}