{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:B5MWPAVDZ6JBJ4TRGNFPRBODI5","short_pith_number":"pith:B5MWPAVD","schema_version":"1.0","canonical_sha256":"0f596782a3cf9214f271334af885c347562a2a779aaac668d80bd3562ef3c1b8","source":{"kind":"arxiv","id":"2211.09873","version":1},"attestation_state":"computed","paper":{"title":"Randomised subspace methods for non-convex optimization, with applications to nonlinear least-squares","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Coralia Cartis, Jaroslav Fowkes, Zhen Shao","submitted_at":"2022-11-17T20:24:48Z","abstract_excerpt":"We propose a general random subspace framework for unconstrained nonconvex optimization problems that requires a weak probabilistic assumption on the subspace gradient, which we show to be satisfied by various random matrix ensembles, such as Gaussian and sparse sketching, using Johnson-Lindenstrauss embedding properties. We show that, when safeguarded with trust region or quadratic regularization, this random subspace approach satisfies, with high probability, a complexity bound of order $\\mathcal{O}(\\epsilon^{-2})$ to drive the (full) gradient below $\\epsilon$; matching in the accuracy order"},"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":"2211.09873","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2022-11-17T20:24:48Z","cross_cats_sorted":[],"title_canon_sha256":"f0ee0029a119fd1fa6490329de7f9c9ec24e8d113a1079dde2c39a8cb62cf8cd","abstract_canon_sha256":"f0940bdfcf6e818daa27a9bd131964eaa2e336b335c70d88a3e9e55da0b89ac1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:15.037460Z","signature_b64":"q4PIppcW3elkIzSnY8HdQzv9rZJC7YL95m4o5r5deiI1V/bc+COgJFkg4EJD/v99CDkTyH1Ift4WeEl8zgZzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f596782a3cf9214f271334af885c347562a2a779aaac668d80bd3562ef3c1b8","last_reissued_at":"2026-07-05T05:17:15.036977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:15.036977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Randomised subspace methods for non-convex optimization, with applications to nonlinear least-squares","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Coralia Cartis, Jaroslav Fowkes, Zhen Shao","submitted_at":"2022-11-17T20:24:48Z","abstract_excerpt":"We propose a general random subspace framework for unconstrained nonconvex optimization problems that requires a weak probabilistic assumption on the subspace gradient, which we show to be satisfied by various random matrix ensembles, such as Gaussian and sparse sketching, using Johnson-Lindenstrauss embedding properties. We show that, when safeguarded with trust region or quadratic regularization, this random subspace approach satisfies, with high probability, a complexity bound of order $\\mathcal{O}(\\epsilon^{-2})$ to drive the (full) gradient below $\\epsilon$; matching in the accuracy order"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09873","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/2211.09873/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":"2211.09873","created_at":"2026-07-05T05:17:15.037039+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09873v1","created_at":"2026-07-05T05:17:15.037039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09873","created_at":"2026-07-05T05:17:15.037039+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5MWPAVDZ6JB","created_at":"2026-07-05T05:17:15.037039+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5MWPAVDZ6JBJ4TR","created_at":"2026-07-05T05:17:15.037039+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5MWPAVD","created_at":"2026-07-05T05:17:15.037039+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.20335","citing_title":"CLARSTA: A random subspace trust-region algorithm for convex-constrained derivative-free optimization","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5MWPAVDZ6JBJ4TRGNFPRBODI5","json":"https://pith.science/pith/B5MWPAVDZ6JBJ4TRGNFPRBODI5.json","graph_json":"https://pith.science/api/pith-number/B5MWPAVDZ6JBJ4TRGNFPRBODI5/graph.json","events_json":"https://pith.science/api/pith-number/B5MWPAVDZ6JBJ4TRGNFPRBODI5/events.json","paper":"https://pith.science/paper/B5MWPAVD"},"agent_actions":{"view_html":"https://pith.science/pith/B5MWPAVDZ6JBJ4TRGNFPRBODI5","download_json":"https://pith.science/pith/B5MWPAVDZ6JBJ4TRGNFPRBODI5.json","view_paper":"https://pith.science/paper/B5MWPAVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09873&json=true","fetch_graph":"https://pith.science/api/pith-number/B5MWPAVDZ6JBJ4TRGNFPRBODI5/graph.json","fetch_events":"https://pith.science/api/pith-number/B5MWPAVDZ6JBJ4TRGNFPRBODI5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5MWPAVDZ6JBJ4TRGNFPRBODI5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5MWPAVDZ6JBJ4TRGNFPRBODI5/action/storage_attestation","attest_author":"https://pith.science/pith/B5MWPAVDZ6JBJ4TRGNFPRBODI5/action/author_attestation","sign_citation":"https://pith.science/pith/B5MWPAVDZ6JBJ4TRGNFPRBODI5/action/citation_signature","submit_replication":"https://pith.science/pith/B5MWPAVDZ6JBJ4TRGNFPRBODI5/action/replication_record"}},"created_at":"2026-07-05T05:17:15.037039+00:00","updated_at":"2026-07-05T05:17:15.037039+00:00"}