{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AAUTYHO2YF2Z7RZHNQN7SADR4F","short_pith_number":"pith:AAUTYHO2","schema_version":"1.0","canonical_sha256":"00293c1ddac1759fc7276c1bf90071e15500a17f538933b064a0114a8d2f375c","source":{"kind":"arxiv","id":"2002.03687","version":2},"attestation_state":"computed","paper":{"title":"SPAN: A Stochastic Projected Approximate Newton Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Lei Li, Linyun Yu, Xianfeng Liang, Xunpeng Huang, Yitan Li, Yue Yu, Zhengyang Liu","submitted_at":"2020-02-10T12:42:42Z","abstract_excerpt":"Second-order optimization methods have desirable convergence properties. However, the exact Newton method requires expensive computation for the Hessian and its inverse. In this paper, we propose SPAN, a novel approximate and fast Newton method. SPAN computes the inverse of the Hessian matrix via low-rank approximation and stochastic Hessian-vector products. Our experiments on multiple benchmark datasets demonstrate that SPAN outperforms existing first-order and second-order optimization methods in terms of the convergence wall-clock time. Furthermore, we provide a theoretical analysis of the "},"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":"2002.03687","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-02-10T12:42:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"256c2e871c43a094a6592167f10b0256caecf9c7a8526bc07f84a46d56aef93f","abstract_canon_sha256":"9a1dcfcdcefb8e59184acb5f8118a710c1271afb553d53507298f5527ca64ed3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:45:23.090946Z","signature_b64":"Z6T+DiQIY6I1QJSsvSLb06hQd69WUtUCa7FUdO5Eoruu0WdLgcwLhFTElZQzU7titU85DptUvNg58i/GvvPQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00293c1ddac1759fc7276c1bf90071e15500a17f538933b064a0114a8d2f375c","last_reissued_at":"2026-07-05T00:45:23.090448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:45:23.090448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPAN: A Stochastic Projected Approximate Newton Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Lei Li, Linyun Yu, Xianfeng Liang, Xunpeng Huang, Yitan Li, Yue Yu, Zhengyang Liu","submitted_at":"2020-02-10T12:42:42Z","abstract_excerpt":"Second-order optimization methods have desirable convergence properties. However, the exact Newton method requires expensive computation for the Hessian and its inverse. In this paper, we propose SPAN, a novel approximate and fast Newton method. SPAN computes the inverse of the Hessian matrix via low-rank approximation and stochastic Hessian-vector products. Our experiments on multiple benchmark datasets demonstrate that SPAN outperforms existing first-order and second-order optimization methods in terms of the convergence wall-clock time. Furthermore, we provide a theoretical analysis of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03687","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/2002.03687/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":"2002.03687","created_at":"2026-07-05T00:45:23.090514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.03687v2","created_at":"2026-07-05T00:45:23.090514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03687","created_at":"2026-07-05T00:45:23.090514+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAUTYHO2YF2Z","created_at":"2026-07-05T00:45:23.090514+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAUTYHO2YF2Z7RZH","created_at":"2026-07-05T00:45:23.090514+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAUTYHO2","created_at":"2026-07-05T00:45:23.090514+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/AAUTYHO2YF2Z7RZHNQN7SADR4F","json":"https://pith.science/pith/AAUTYHO2YF2Z7RZHNQN7SADR4F.json","graph_json":"https://pith.science/api/pith-number/AAUTYHO2YF2Z7RZHNQN7SADR4F/graph.json","events_json":"https://pith.science/api/pith-number/AAUTYHO2YF2Z7RZHNQN7SADR4F/events.json","paper":"https://pith.science/paper/AAUTYHO2"},"agent_actions":{"view_html":"https://pith.science/pith/AAUTYHO2YF2Z7RZHNQN7SADR4F","download_json":"https://pith.science/pith/AAUTYHO2YF2Z7RZHNQN7SADR4F.json","view_paper":"https://pith.science/paper/AAUTYHO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.03687&json=true","fetch_graph":"https://pith.science/api/pith-number/AAUTYHO2YF2Z7RZHNQN7SADR4F/graph.json","fetch_events":"https://pith.science/api/pith-number/AAUTYHO2YF2Z7RZHNQN7SADR4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAUTYHO2YF2Z7RZHNQN7SADR4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAUTYHO2YF2Z7RZHNQN7SADR4F/action/storage_attestation","attest_author":"https://pith.science/pith/AAUTYHO2YF2Z7RZHNQN7SADR4F/action/author_attestation","sign_citation":"https://pith.science/pith/AAUTYHO2YF2Z7RZHNQN7SADR4F/action/citation_signature","submit_replication":"https://pith.science/pith/AAUTYHO2YF2Z7RZHNQN7SADR4F/action/replication_record"}},"created_at":"2026-07-05T00:45:23.090514+00:00","updated_at":"2026-07-05T00:45:23.090514+00:00"}