{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SDFVBILRSS7ACKHGVJCVBGII4Q","short_pith_number":"pith:SDFVBILR","schema_version":"1.0","canonical_sha256":"90cb50a17194be0128e6aa45509908e4015fdcf21920e3b3abd8239b2ba4ff5b","source":{"kind":"arxiv","id":"2308.09912","version":2},"attestation_state":"computed","paper":{"title":"Complexity Guarantees for Nonconvex Newton-MR Under Inexact Hessian Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Alexander Lim, Fred Roosta","submitted_at":"2023-08-19T05:36:00Z","abstract_excerpt":"We consider an extension of the Newton-MR algorithm for nonconvex unconstrained optimization to the settings where Hessian information is approximated. Under a particular noise model on the Hessian matrix, we investigate the iteration and operation complexities of this variant to achieve appropriate sub-optimality criteria in several nonconvex settings. We do this by first considering functions that satisfy the (generalized) Polyak-\\L ojasiewicz condition, a special sub-class of nonconvex functions. We show that, under certain conditions, our algorithm achieves global linear convergence rate. "},"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":"2308.09912","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-08-19T05:36:00Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"55d50022c1f4f6058d6f222e03947d3708d1dae109bd5e88727d04f0b4833e9a","abstract_canon_sha256":"e46b64783e24fa4e71b3ecb7b4f206ef6445e6108a3577cbad2637bd168e1826"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:24.073943Z","signature_b64":"1f6OiQVu7pbk0pZONIsHNvAu9DgGbUh6vbA//r/o/Vrkbgs2/jAG7vHQ6QCnlzt6Fq5IN3Vt4N1LkmG3uylfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90cb50a17194be0128e6aa45509908e4015fdcf21920e3b3abd8239b2ba4ff5b","last_reissued_at":"2026-07-05T09:06:24.073520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:24.073520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complexity Guarantees for Nonconvex Newton-MR Under Inexact Hessian Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Alexander Lim, Fred Roosta","submitted_at":"2023-08-19T05:36:00Z","abstract_excerpt":"We consider an extension of the Newton-MR algorithm for nonconvex unconstrained optimization to the settings where Hessian information is approximated. Under a particular noise model on the Hessian matrix, we investigate the iteration and operation complexities of this variant to achieve appropriate sub-optimality criteria in several nonconvex settings. We do this by first considering functions that satisfy the (generalized) Polyak-\\L ojasiewicz condition, a special sub-class of nonconvex functions. We show that, under certain conditions, our algorithm achieves global linear convergence rate. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09912","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/2308.09912/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":"2308.09912","created_at":"2026-07-05T09:06:24.073576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.09912v2","created_at":"2026-07-05T09:06:24.073576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09912","created_at":"2026-07-05T09:06:24.073576+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDFVBILRSS7A","created_at":"2026-07-05T09:06:24.073576+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDFVBILRSS7ACKHG","created_at":"2026-07-05T09:06:24.073576+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDFVBILR","created_at":"2026-07-05T09:06:24.073576+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03701","citing_title":"First-ish Order Methods: Hessian-aware Scalings of Gradient Descent","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDFVBILRSS7ACKHGVJCVBGII4Q","json":"https://pith.science/pith/SDFVBILRSS7ACKHGVJCVBGII4Q.json","graph_json":"https://pith.science/api/pith-number/SDFVBILRSS7ACKHGVJCVBGII4Q/graph.json","events_json":"https://pith.science/api/pith-number/SDFVBILRSS7ACKHGVJCVBGII4Q/events.json","paper":"https://pith.science/paper/SDFVBILR"},"agent_actions":{"view_html":"https://pith.science/pith/SDFVBILRSS7ACKHGVJCVBGII4Q","download_json":"https://pith.science/pith/SDFVBILRSS7ACKHGVJCVBGII4Q.json","view_paper":"https://pith.science/paper/SDFVBILR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.09912&json=true","fetch_graph":"https://pith.science/api/pith-number/SDFVBILRSS7ACKHGVJCVBGII4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/SDFVBILRSS7ACKHGVJCVBGII4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDFVBILRSS7ACKHGVJCVBGII4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDFVBILRSS7ACKHGVJCVBGII4Q/action/storage_attestation","attest_author":"https://pith.science/pith/SDFVBILRSS7ACKHGVJCVBGII4Q/action/author_attestation","sign_citation":"https://pith.science/pith/SDFVBILRSS7ACKHGVJCVBGII4Q/action/citation_signature","submit_replication":"https://pith.science/pith/SDFVBILRSS7ACKHGVJCVBGII4Q/action/replication_record"}},"created_at":"2026-07-05T09:06:24.073576+00:00","updated_at":"2026-07-05T09:06:24.073576+00:00"}