{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QPLUYHR43ACISB5PLZAWYWXGJD","short_pith_number":"pith:QPLUYHR4","schema_version":"1.0","canonical_sha256":"83d74c1e3cd8048907af5e416c5ae648f9bfbb5964ca04b9ef2c83e764812a0a","source":{"kind":"arxiv","id":"2406.16666","version":2},"attestation_state":"computed","paper":{"title":"Cubic regularized subspace Newton for non-convex optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC"],"primary_cat":"cs.LG","authors_text":"Aurelien Lucchi, Jim Zhao, Nikita Doikov","submitted_at":"2024-06-24T14:20:02Z","abstract_excerpt":"This paper addresses the optimization problem of minimizing non-convex continuous functions, which is relevant in the context of high-dimensional machine learning applications characterized by over-parametrization. We analyze a randomized coordinate second-order method named SSCN which can be interpreted as applying cubic regularization in random subspaces. This approach effectively reduces the computational complexity associated with utilizing second-order information, rendering it applicable in higher-dimensional scenarios. Theoretically, we establish convergence guarantees for non-convex fu"},"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":"2406.16666","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T14:20:02Z","cross_cats_sorted":["cs.NA","math.NA","math.OC"],"title_canon_sha256":"f8afbb8e3d65193228e4e3d2c5b8b3318bb04053e259513ce3dc0960c4edb7da","abstract_canon_sha256":"ba2415bc292c62be5e30db3a3ff33a5109ea66b85b71c505e99bb85c08a3a7e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:03.561896Z","signature_b64":"2XnyulklMguRXlwClXAoJpyJVwZVzYTaYs49jnWCz1ncOSnTfdOmlN8snuyzr9ziIhOUwEcrPYBqQS+o8p6PBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83d74c1e3cd8048907af5e416c5ae648f9bfbb5964ca04b9ef2c83e764812a0a","last_reissued_at":"2026-07-05T10:21:03.561380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:03.561380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cubic regularized subspace Newton for non-convex optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC"],"primary_cat":"cs.LG","authors_text":"Aurelien Lucchi, Jim Zhao, Nikita Doikov","submitted_at":"2024-06-24T14:20:02Z","abstract_excerpt":"This paper addresses the optimization problem of minimizing non-convex continuous functions, which is relevant in the context of high-dimensional machine learning applications characterized by over-parametrization. We analyze a randomized coordinate second-order method named SSCN which can be interpreted as applying cubic regularization in random subspaces. This approach effectively reduces the computational complexity associated with utilizing second-order information, rendering it applicable in higher-dimensional scenarios. Theoretically, we establish convergence guarantees for non-convex fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16666","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/2406.16666/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":"2406.16666","created_at":"2026-07-05T10:21:03.561444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16666v2","created_at":"2026-07-05T10:21:03.561444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16666","created_at":"2026-07-05T10:21:03.561444+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPLUYHR43ACI","created_at":"2026-07-05T10:21:03.561444+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPLUYHR43ACISB5P","created_at":"2026-07-05T10:21:03.561444+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPLUYHR4","created_at":"2026-07-05T10:21:03.561444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24600","citing_title":"Bridging Identification and Second-Order Acceleration: A Fast Alternating Minimization Framework for Composite Optimization","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPLUYHR43ACISB5PLZAWYWXGJD","json":"https://pith.science/pith/QPLUYHR43ACISB5PLZAWYWXGJD.json","graph_json":"https://pith.science/api/pith-number/QPLUYHR43ACISB5PLZAWYWXGJD/graph.json","events_json":"https://pith.science/api/pith-number/QPLUYHR43ACISB5PLZAWYWXGJD/events.json","paper":"https://pith.science/paper/QPLUYHR4"},"agent_actions":{"view_html":"https://pith.science/pith/QPLUYHR43ACISB5PLZAWYWXGJD","download_json":"https://pith.science/pith/QPLUYHR43ACISB5PLZAWYWXGJD.json","view_paper":"https://pith.science/paper/QPLUYHR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16666&json=true","fetch_graph":"https://pith.science/api/pith-number/QPLUYHR43ACISB5PLZAWYWXGJD/graph.json","fetch_events":"https://pith.science/api/pith-number/QPLUYHR43ACISB5PLZAWYWXGJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPLUYHR43ACISB5PLZAWYWXGJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPLUYHR43ACISB5PLZAWYWXGJD/action/storage_attestation","attest_author":"https://pith.science/pith/QPLUYHR43ACISB5PLZAWYWXGJD/action/author_attestation","sign_citation":"https://pith.science/pith/QPLUYHR43ACISB5PLZAWYWXGJD/action/citation_signature","submit_replication":"https://pith.science/pith/QPLUYHR43ACISB5PLZAWYWXGJD/action/replication_record"}},"created_at":"2026-07-05T10:21:03.561444+00:00","updated_at":"2026-07-05T10:21:03.561444+00:00"}