{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TXK3ODBLBMZ5J3VEUGKWKKNKY5","short_pith_number":"pith:TXK3ODBL","schema_version":"1.0","canonical_sha256":"9dd5b70c2b0b33d4eea4a1956529aac76ab22399ce88f0ac0e2db5faa9cd8b62","source":{"kind":"arxiv","id":"2310.18841","version":2},"attestation_state":"computed","paper":{"title":"A randomized algorithm for nonconvex minimization with inexact evaluations and complexity guarantees","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Shuyao Li, Stephen J. Wright","submitted_at":"2023-10-28T22:57:56Z","abstract_excerpt":"We consider minimization of a smooth nonconvex function with inexact oracle access to gradient and Hessian (without assuming access to the function value) to achieve approximate second-order optimality. A novel feature of our method is that if an approximate direction of negative curvature is chosen as the step, we choose its sense to be positive or negative with equal probability. We allow gradients to be inexact in a relative sense and relax the coupling between inexactness thresholds for the first- and second-order optimality conditions. Our convergence analysis includes both an expectation"},"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":"2310.18841","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"math.OC","submitted_at":"2023-10-28T22:57:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"870b9f1e7b7d7fb77605835b2b6f2af0c4ed6994ff0a691e85838a184e49f414","abstract_canon_sha256":"f19c9eee640fc6afd7790dd9761d5aae78e92dbfe4ab4fd291aeb4cc75f4ebac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:37.420339Z","signature_b64":"1h+/Rvu2xGuHgf6uZAtuxPNFLBlLKjoyW0qrfHZ7KFqJFCCsNAgyaj325N+1a9RLPQhr+SDchTXkmh++efyLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dd5b70c2b0b33d4eea4a1956529aac76ab22399ce88f0ac0e2db5faa9cd8b62","last_reissued_at":"2026-07-05T08:00:37.419725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:37.419725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A randomized algorithm for nonconvex minimization with inexact evaluations and complexity guarantees","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Shuyao Li, Stephen J. Wright","submitted_at":"2023-10-28T22:57:56Z","abstract_excerpt":"We consider minimization of a smooth nonconvex function with inexact oracle access to gradient and Hessian (without assuming access to the function value) to achieve approximate second-order optimality. A novel feature of our method is that if an approximate direction of negative curvature is chosen as the step, we choose its sense to be positive or negative with equal probability. We allow gradients to be inexact in a relative sense and relax the coupling between inexactness thresholds for the first- and second-order optimality conditions. Our convergence analysis includes both an expectation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18841","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/2310.18841/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":"2310.18841","created_at":"2026-07-05T08:00:37.419798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18841v2","created_at":"2026-07-05T08:00:37.419798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18841","created_at":"2026-07-05T08:00:37.419798+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXK3ODBLBMZ5","created_at":"2026-07-05T08:00:37.419798+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXK3ODBLBMZ5J3VE","created_at":"2026-07-05T08:00:37.419798+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXK3ODBL","created_at":"2026-07-05T08:00:37.419798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10378","citing_title":"Exploiting Negative Curvature in Conjunction with Adaptive Sampling: Theoretical Results and a Practical Algorithm","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TXK3ODBLBMZ5J3VEUGKWKKNKY5","json":"https://pith.science/pith/TXK3ODBLBMZ5J3VEUGKWKKNKY5.json","graph_json":"https://pith.science/api/pith-number/TXK3ODBLBMZ5J3VEUGKWKKNKY5/graph.json","events_json":"https://pith.science/api/pith-number/TXK3ODBLBMZ5J3VEUGKWKKNKY5/events.json","paper":"https://pith.science/paper/TXK3ODBL"},"agent_actions":{"view_html":"https://pith.science/pith/TXK3ODBLBMZ5J3VEUGKWKKNKY5","download_json":"https://pith.science/pith/TXK3ODBLBMZ5J3VEUGKWKKNKY5.json","view_paper":"https://pith.science/paper/TXK3ODBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18841&json=true","fetch_graph":"https://pith.science/api/pith-number/TXK3ODBLBMZ5J3VEUGKWKKNKY5/graph.json","fetch_events":"https://pith.science/api/pith-number/TXK3ODBLBMZ5J3VEUGKWKKNKY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXK3ODBLBMZ5J3VEUGKWKKNKY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXK3ODBLBMZ5J3VEUGKWKKNKY5/action/storage_attestation","attest_author":"https://pith.science/pith/TXK3ODBLBMZ5J3VEUGKWKKNKY5/action/author_attestation","sign_citation":"https://pith.science/pith/TXK3ODBLBMZ5J3VEUGKWKKNKY5/action/citation_signature","submit_replication":"https://pith.science/pith/TXK3ODBLBMZ5J3VEUGKWKKNKY5/action/replication_record"}},"created_at":"2026-07-05T08:00:37.419798+00:00","updated_at":"2026-07-05T08:00:37.419798+00:00"}