{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XPEZ2A6WR7SZYJ6OU44LH5JI7E","short_pith_number":"pith:XPEZ2A6W","schema_version":"1.0","canonical_sha256":"bbc99d03d68fe59c27cea738b3f528f90025de5751e0389872c0d0c7ec35e088","source":{"kind":"arxiv","id":"2006.09606","version":2},"attestation_state":"computed","paper":{"title":"Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Dong Xu, Hongyu Chen, Mengyun Chen, Minghan Yang, Zaiwen Wen","submitted_at":"2020-06-17T02:16:51Z","abstract_excerpt":"In this paper, we consider stochastic second-order methods for minimizing a finite summation of nonconvex functions. One important key is to find an ingenious but cheap scheme to incorporate local curvature information. Since the true Hessian matrix is often a combination of a cheap part and an expensive part, we propose a structured stochastic quasi-Newton method by using partial Hessian information as much as possible. By further exploiting either the low-rank structure or the kronecker-product properties of the quasi-Newton approximations, the computation of the quasi-Newton direction is af"},"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":"2006.09606","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-17T02:16:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"75fa167696f380c1e135347ea39c5aa8666414cb427356c86ae88cedfd8af955","abstract_canon_sha256":"e5654e6b01e48dfcdc0ae66b6fe33217ccde6383698f52444f45c8d799b0f649"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:12.313478Z","signature_b64":"AV55SBGNZnsoJVYSUGfwccPMkT/MbUOiV3kCZQciHxwSbAjP8tS3vpJB9OTqWiHz/vLUnGJKGzqkx0izhaSBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbc99d03d68fe59c27cea738b3f528f90025de5751e0389872c0d0c7ec35e088","last_reissued_at":"2026-07-05T02:26:12.312976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:12.312976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Dong Xu, Hongyu Chen, Mengyun Chen, Minghan Yang, Zaiwen Wen","submitted_at":"2020-06-17T02:16:51Z","abstract_excerpt":"In this paper, we consider stochastic second-order methods for minimizing a finite summation of nonconvex functions. One important key is to find an ingenious but cheap scheme to incorporate local curvature information. Since the true Hessian matrix is often a combination of a cheap part and an expensive part, we propose a structured stochastic quasi-Newton method by using partial Hessian information as much as possible. By further exploiting either the low-rank structure or the kronecker-product properties of the quasi-Newton approximations, the computation of the quasi-Newton direction is af"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09606","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/2006.09606/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":"2006.09606","created_at":"2026-07-05T02:26:12.313033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.09606v2","created_at":"2026-07-05T02:26:12.313033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09606","created_at":"2026-07-05T02:26:12.313033+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPEZ2A6WR7SZ","created_at":"2026-07-05T02:26:12.313033+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPEZ2A6WR7SZYJ6O","created_at":"2026-07-05T02:26:12.313033+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPEZ2A6W","created_at":"2026-07-05T02:26:12.313033+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/XPEZ2A6WR7SZYJ6OU44LH5JI7E","json":"https://pith.science/pith/XPEZ2A6WR7SZYJ6OU44LH5JI7E.json","graph_json":"https://pith.science/api/pith-number/XPEZ2A6WR7SZYJ6OU44LH5JI7E/graph.json","events_json":"https://pith.science/api/pith-number/XPEZ2A6WR7SZYJ6OU44LH5JI7E/events.json","paper":"https://pith.science/paper/XPEZ2A6W"},"agent_actions":{"view_html":"https://pith.science/pith/XPEZ2A6WR7SZYJ6OU44LH5JI7E","download_json":"https://pith.science/pith/XPEZ2A6WR7SZYJ6OU44LH5JI7E.json","view_paper":"https://pith.science/paper/XPEZ2A6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.09606&json=true","fetch_graph":"https://pith.science/api/pith-number/XPEZ2A6WR7SZYJ6OU44LH5JI7E/graph.json","fetch_events":"https://pith.science/api/pith-number/XPEZ2A6WR7SZYJ6OU44LH5JI7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPEZ2A6WR7SZYJ6OU44LH5JI7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPEZ2A6WR7SZYJ6OU44LH5JI7E/action/storage_attestation","attest_author":"https://pith.science/pith/XPEZ2A6WR7SZYJ6OU44LH5JI7E/action/author_attestation","sign_citation":"https://pith.science/pith/XPEZ2A6WR7SZYJ6OU44LH5JI7E/action/citation_signature","submit_replication":"https://pith.science/pith/XPEZ2A6WR7SZYJ6OU44LH5JI7E/action/replication_record"}},"created_at":"2026-07-05T02:26:12.313033+00:00","updated_at":"2026-07-05T02:26:12.313033+00:00"}