{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PA7OGPHCMKOTZ66PNOU53BCFEF","short_pith_number":"pith:PA7OGPHC","schema_version":"1.0","canonical_sha256":"783ee33ce2629d3cfbcf6ba9dd844521499b85234a85afcfd052f75e12563f56","source":{"kind":"arxiv","id":"2311.13094","version":3},"attestation_state":"computed","paper":{"title":"Newton-CG methods for nonconvex unconstrained optimization with H\\\"older continuous Hessian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Chuan He, Heng Huang, Zhaosong Lu","submitted_at":"2023-11-22T01:50:43Z","abstract_excerpt":"In this paper we consider a nonconvex unconstrained optimization problem minimizing a twice differentiable objective function with H\\\"older continuous Hessian. Specifically, we first propose a Newton-conjugate gradient (Newton-CG) method for finding an approximate first- and second-order stationary point of this problem, assuming the associated the H\\\"older parameters are explicitly known. Then we develop a parameter-free Newton-CG method without requiring any prior knowledge of these parameters. To the best of our knowledge, this method is the first parameter-free second-order method achievin"},"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":"2311.13094","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-11-22T01:50:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"31f7d03cf16037c7312d38f92cff9a21ef352afa6326f99b5873d8058bef481f","abstract_canon_sha256":"7d0d9f399e1ab509831d42396a39b39c24a762dd3e08a6b12a5c357f65924ce9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:13.819251Z","signature_b64":"WtY7An7HH5mNNYXrOBDcIBJEBylthTcIjido37Q5/DAlSLocTjK2kHvK1Xa2FTRvsy6v2IqddEq2Ppy+wBYNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"783ee33ce2629d3cfbcf6ba9dd844521499b85234a85afcfd052f75e12563f56","last_reissued_at":"2026-07-05T10:48:13.818804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:13.818804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Newton-CG methods for nonconvex unconstrained optimization with H\\\"older continuous Hessian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Chuan He, Heng Huang, Zhaosong Lu","submitted_at":"2023-11-22T01:50:43Z","abstract_excerpt":"In this paper we consider a nonconvex unconstrained optimization problem minimizing a twice differentiable objective function with H\\\"older continuous Hessian. Specifically, we first propose a Newton-conjugate gradient (Newton-CG) method for finding an approximate first- and second-order stationary point of this problem, assuming the associated the H\\\"older parameters are explicitly known. Then we develop a parameter-free Newton-CG method without requiring any prior knowledge of these parameters. To the best of our knowledge, this method is the first parameter-free second-order method achievin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13094","kind":"arxiv","version":3},"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/2311.13094/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":"2311.13094","created_at":"2026-07-05T10:48:13.818861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13094v3","created_at":"2026-07-05T10:48:13.818861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13094","created_at":"2026-07-05T10:48:13.818861+00:00"},{"alias_kind":"pith_short_12","alias_value":"PA7OGPHCMKOT","created_at":"2026-07-05T10:48:13.818861+00:00"},{"alias_kind":"pith_short_16","alias_value":"PA7OGPHCMKOTZ66P","created_at":"2026-07-05T10:48:13.818861+00:00"},{"alias_kind":"pith_short_8","alias_value":"PA7OGPHC","created_at":"2026-07-05T10:48:13.818861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02079","citing_title":"A simple and practical adaptive trust-region method","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PA7OGPHCMKOTZ66PNOU53BCFEF","json":"https://pith.science/pith/PA7OGPHCMKOTZ66PNOU53BCFEF.json","graph_json":"https://pith.science/api/pith-number/PA7OGPHCMKOTZ66PNOU53BCFEF/graph.json","events_json":"https://pith.science/api/pith-number/PA7OGPHCMKOTZ66PNOU53BCFEF/events.json","paper":"https://pith.science/paper/PA7OGPHC"},"agent_actions":{"view_html":"https://pith.science/pith/PA7OGPHCMKOTZ66PNOU53BCFEF","download_json":"https://pith.science/pith/PA7OGPHCMKOTZ66PNOU53BCFEF.json","view_paper":"https://pith.science/paper/PA7OGPHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13094&json=true","fetch_graph":"https://pith.science/api/pith-number/PA7OGPHCMKOTZ66PNOU53BCFEF/graph.json","fetch_events":"https://pith.science/api/pith-number/PA7OGPHCMKOTZ66PNOU53BCFEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PA7OGPHCMKOTZ66PNOU53BCFEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PA7OGPHCMKOTZ66PNOU53BCFEF/action/storage_attestation","attest_author":"https://pith.science/pith/PA7OGPHCMKOTZ66PNOU53BCFEF/action/author_attestation","sign_citation":"https://pith.science/pith/PA7OGPHCMKOTZ66PNOU53BCFEF/action/citation_signature","submit_replication":"https://pith.science/pith/PA7OGPHCMKOTZ66PNOU53BCFEF/action/replication_record"}},"created_at":"2026-07-05T10:48:13.818861+00:00","updated_at":"2026-07-05T10:48:13.818861+00:00"}