{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FD4K7ZBQ5FFQOTTTJKPWWXR7OQ","short_pith_number":"pith:FD4K7ZBQ","schema_version":"1.0","canonical_sha256":"28f8afe430e94b074e734a9f6b5e3f74189b9fbd968422ce16d5271ee8ce3de5","source":{"kind":"arxiv","id":"2211.05727","version":1},"attestation_state":"computed","paper":{"title":"A Randomised Subspace Gauss-Newton Method for Nonlinear Least-Squares","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Coralia Cartis, Jaroslav Fowkes, Zhen Shao","submitted_at":"2022-11-10T17:51:08Z","abstract_excerpt":"We propose a Randomised Subspace Gauss-Newton (R-SGN) algorithm for solving nonlinear least-squares optimization problems, that uses a sketched Jacobian of the residual in the variable domain and solves a reduced linear least-squares on each iteration. A sublinear global rate of convergence result is presented for a trust-region variant of R-SGN, with high probability, which matches deterministic counterpart results in the order of the accuracy tolerance. Promising preliminary numerical results are presented for R-SGN on logistic regression and on nonlinear regression problems from the CUTEst "},"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":"2211.05727","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2022-11-10T17:51:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e4a76a7ad232c67ea6c7f79edafe44a848ef35dc05b0b9664145849c02fecb6d","abstract_canon_sha256":"c472d826cd9f18c6c1e2c3d4f7b80fa48bc7170e17e7e73061c701725e0e1b51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:07.210613Z","signature_b64":"VFQ8Pqg3QBpzjx859nqrGS+fK+vlCSbh56MesYXahr/ZmgSL3NPPyw40E4QCeylqZEGm6NkE/m0P/Gwcp6MzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28f8afe430e94b074e734a9f6b5e3f74189b9fbd968422ce16d5271ee8ce3de5","last_reissued_at":"2026-07-05T05:15:07.210267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:07.210267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Randomised Subspace Gauss-Newton Method for Nonlinear Least-Squares","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Coralia Cartis, Jaroslav Fowkes, Zhen Shao","submitted_at":"2022-11-10T17:51:08Z","abstract_excerpt":"We propose a Randomised Subspace Gauss-Newton (R-SGN) algorithm for solving nonlinear least-squares optimization problems, that uses a sketched Jacobian of the residual in the variable domain and solves a reduced linear least-squares on each iteration. A sublinear global rate of convergence result is presented for a trust-region variant of R-SGN, with high probability, which matches deterministic counterpart results in the order of the accuracy tolerance. Promising preliminary numerical results are presented for R-SGN on logistic regression and on nonlinear regression problems from the CUTEst "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05727","kind":"arxiv","version":1},"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/2211.05727/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":"2211.05727","created_at":"2026-07-05T05:15:07.210321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.05727v1","created_at":"2026-07-05T05:15:07.210321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05727","created_at":"2026-07-05T05:15:07.210321+00:00"},{"alias_kind":"pith_short_12","alias_value":"FD4K7ZBQ5FFQ","created_at":"2026-07-05T05:15:07.210321+00:00"},{"alias_kind":"pith_short_16","alias_value":"FD4K7ZBQ5FFQOTTT","created_at":"2026-07-05T05:15:07.210321+00:00"},{"alias_kind":"pith_short_8","alias_value":"FD4K7ZBQ","created_at":"2026-07-05T05:15:07.210321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.03162","citing_title":"On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FD4K7ZBQ5FFQOTTTJKPWWXR7OQ","json":"https://pith.science/pith/FD4K7ZBQ5FFQOTTTJKPWWXR7OQ.json","graph_json":"https://pith.science/api/pith-number/FD4K7ZBQ5FFQOTTTJKPWWXR7OQ/graph.json","events_json":"https://pith.science/api/pith-number/FD4K7ZBQ5FFQOTTTJKPWWXR7OQ/events.json","paper":"https://pith.science/paper/FD4K7ZBQ"},"agent_actions":{"view_html":"https://pith.science/pith/FD4K7ZBQ5FFQOTTTJKPWWXR7OQ","download_json":"https://pith.science/pith/FD4K7ZBQ5FFQOTTTJKPWWXR7OQ.json","view_paper":"https://pith.science/paper/FD4K7ZBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.05727&json=true","fetch_graph":"https://pith.science/api/pith-number/FD4K7ZBQ5FFQOTTTJKPWWXR7OQ/graph.json","fetch_events":"https://pith.science/api/pith-number/FD4K7ZBQ5FFQOTTTJKPWWXR7OQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FD4K7ZBQ5FFQOTTTJKPWWXR7OQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FD4K7ZBQ5FFQOTTTJKPWWXR7OQ/action/storage_attestation","attest_author":"https://pith.science/pith/FD4K7ZBQ5FFQOTTTJKPWWXR7OQ/action/author_attestation","sign_citation":"https://pith.science/pith/FD4K7ZBQ5FFQOTTTJKPWWXR7OQ/action/citation_signature","submit_replication":"https://pith.science/pith/FD4K7ZBQ5FFQOTTTJKPWWXR7OQ/action/replication_record"}},"created_at":"2026-07-05T05:15:07.210321+00:00","updated_at":"2026-07-05T05:15:07.210321+00:00"}