{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NKUXPWVZH7JOZHPMOUQHKYHVPE","short_pith_number":"pith:NKUXPWVZ","schema_version":"1.0","canonical_sha256":"6aa977dab93fd2ec9dec75207560f579389e19a4da607365d9f351c3edb5abc7","source":{"kind":"arxiv","id":"1902.04952","version":2},"attestation_state":"computed","paper":{"title":"Do Subsampled Newton Methods Work for High-Dimensional Data?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Shusen Wang, Xiang Li, Zhihua Zhang","submitted_at":"2019-02-13T15:30:10Z","abstract_excerpt":"Subsampled Newton methods approximate Hessian matrices through subsampling techniques, alleviating the cost of forming Hessian matrices but using sufficient curvature information. However, previous results require $\\Omega (d)$ samples to approximate Hessians, where $d$ is the dimension of data points, making it less practically feasible for high-dimensional data. The situation is deteriorated when $d$ is comparably as large as the number of data points $n$, which requires to take the whole dataset into account, making subsampling useless. This paper theoretically justifies the effectiveness of"},"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":"1902.04952","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-13T15:30:10Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"668db94dbf475ba6e68a9c367ffa200f2787cecb6346f511b8a6220314acfe8b","abstract_canon_sha256":"a91988e948e2523a65420d03df3ab16bef909a39580f87970b2aca74866c0da9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:01.874390Z","signature_b64":"3hWjfie3Jtmfim+6BX9rDVzNEMN/8R+w/JgXqARRwYb79SxfysSA5fnPqkcBPqFlSSx4KhRFr6N0mqORXdnhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6aa977dab93fd2ec9dec75207560f579389e19a4da607365d9f351c3edb5abc7","last_reissued_at":"2026-05-17T23:47:01.873667Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:01.873667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Subsampled Newton Methods Work for High-Dimensional Data?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Shusen Wang, Xiang Li, Zhihua Zhang","submitted_at":"2019-02-13T15:30:10Z","abstract_excerpt":"Subsampled Newton methods approximate Hessian matrices through subsampling techniques, alleviating the cost of forming Hessian matrices but using sufficient curvature information. However, previous results require $\\Omega (d)$ samples to approximate Hessians, where $d$ is the dimension of data points, making it less practically feasible for high-dimensional data. The situation is deteriorated when $d$ is comparably as large as the number of data points $n$, which requires to take the whole dataset into account, making subsampling useless. This paper theoretically justifies the effectiveness of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04952","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":""},"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":"1902.04952","created_at":"2026-05-17T23:47:01.873770+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.04952v2","created_at":"2026-05-17T23:47:01.873770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04952","created_at":"2026-05-17T23:47:01.873770+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKUXPWVZH7JO","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKUXPWVZH7JOZHPM","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKUXPWVZ","created_at":"2026-05-18T12:33:24.271573+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/NKUXPWVZH7JOZHPMOUQHKYHVPE","json":"https://pith.science/pith/NKUXPWVZH7JOZHPMOUQHKYHVPE.json","graph_json":"https://pith.science/api/pith-number/NKUXPWVZH7JOZHPMOUQHKYHVPE/graph.json","events_json":"https://pith.science/api/pith-number/NKUXPWVZH7JOZHPMOUQHKYHVPE/events.json","paper":"https://pith.science/paper/NKUXPWVZ"},"agent_actions":{"view_html":"https://pith.science/pith/NKUXPWVZH7JOZHPMOUQHKYHVPE","download_json":"https://pith.science/pith/NKUXPWVZH7JOZHPMOUQHKYHVPE.json","view_paper":"https://pith.science/paper/NKUXPWVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.04952&json=true","fetch_graph":"https://pith.science/api/pith-number/NKUXPWVZH7JOZHPMOUQHKYHVPE/graph.json","fetch_events":"https://pith.science/api/pith-number/NKUXPWVZH7JOZHPMOUQHKYHVPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKUXPWVZH7JOZHPMOUQHKYHVPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKUXPWVZH7JOZHPMOUQHKYHVPE/action/storage_attestation","attest_author":"https://pith.science/pith/NKUXPWVZH7JOZHPMOUQHKYHVPE/action/author_attestation","sign_citation":"https://pith.science/pith/NKUXPWVZH7JOZHPMOUQHKYHVPE/action/citation_signature","submit_replication":"https://pith.science/pith/NKUXPWVZH7JOZHPMOUQHKYHVPE/action/replication_record"}},"created_at":"2026-05-17T23:47:01.873770+00:00","updated_at":"2026-05-17T23:47:01.873770+00:00"}