{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:APCY5ZPESIXO6E4MQDTOXAWAN3","short_pith_number":"pith:APCY5ZPE","schema_version":"1.0","canonical_sha256":"03c58ee5e4922eef138c80e6eb82c06ec6144ebd78f0aaa5c3fe73aadf582a25","source":{"kind":"arxiv","id":"1711.02838","version":2},"attestation_state":"computed","paper":{"title":"Stochastic Cubic Regularization for Fast Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Jin, Jeffrey Regier, Michael I. Jordan, Mitchell Stern, Nilesh Tripuraneni","submitted_at":"2017-11-08T05:39:46Z","abstract_excerpt":"This paper proposes a stochastic variant of a classic algorithm---the cubic-regularized Newton method [Nesterov and Polyak 2006]. The proposed algorithm efficiently escapes saddle points and finds approximate local minima for general smooth, nonconvex functions in only $\\mathcal{\\tilde{O}}(\\epsilon^{-3.5})$ stochastic gradient and stochastic Hessian-vector product evaluations. The latter can be computed as efficiently as stochastic gradients. This improves upon the $\\mathcal{\\tilde{O}}(\\epsilon^{-4})$ rate of stochastic gradient descent. Our rate matches the best-known result for finding local"},"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":"1711.02838","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-08T05:39:46Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"146dba2fa8de8eac67b02bc486c54de5ca47725f14bf90f411032695114ebd3f","abstract_canon_sha256":"2ab3d0896bb8d573d1245438edb6677628a3a37217d7d32a47b466bfece5994a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:40.182915Z","signature_b64":"76TnU50nbwOPbhv4fpIKyg04C8nSS6vVdZqxiiEVkLL9HtQlJcDpsTJTtmGSpg6fwVmvgyyvcpWLHJvwX4ooCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03c58ee5e4922eef138c80e6eb82c06ec6144ebd78f0aaa5c3fe73aadf582a25","last_reissued_at":"2026-05-18T00:28:40.182262Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:40.182262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Cubic Regularization for Fast Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Jin, Jeffrey Regier, Michael I. Jordan, Mitchell Stern, Nilesh Tripuraneni","submitted_at":"2017-11-08T05:39:46Z","abstract_excerpt":"This paper proposes a stochastic variant of a classic algorithm---the cubic-regularized Newton method [Nesterov and Polyak 2006]. The proposed algorithm efficiently escapes saddle points and finds approximate local minima for general smooth, nonconvex functions in only $\\mathcal{\\tilde{O}}(\\epsilon^{-3.5})$ stochastic gradient and stochastic Hessian-vector product evaluations. The latter can be computed as efficiently as stochastic gradients. This improves upon the $\\mathcal{\\tilde{O}}(\\epsilon^{-4})$ rate of stochastic gradient descent. Our rate matches the best-known result for finding local"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.02838","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":""},"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":"1711.02838","created_at":"2026-05-18T00:28:40.182370+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.02838v2","created_at":"2026-05-18T00:28:40.182370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.02838","created_at":"2026-05-18T00:28:40.182370+00:00"},{"alias_kind":"pith_short_12","alias_value":"APCY5ZPESIXO","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"APCY5ZPESIXO6E4M","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"APCY5ZPE","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APCY5ZPESIXO6E4MQDTOXAWAN3","json":"https://pith.science/pith/APCY5ZPESIXO6E4MQDTOXAWAN3.json","graph_json":"https://pith.science/api/pith-number/APCY5ZPESIXO6E4MQDTOXAWAN3/graph.json","events_json":"https://pith.science/api/pith-number/APCY5ZPESIXO6E4MQDTOXAWAN3/events.json","paper":"https://pith.science/paper/APCY5ZPE"},"agent_actions":{"view_html":"https://pith.science/pith/APCY5ZPESIXO6E4MQDTOXAWAN3","download_json":"https://pith.science/pith/APCY5ZPESIXO6E4MQDTOXAWAN3.json","view_paper":"https://pith.science/paper/APCY5ZPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.02838&json=true","fetch_graph":"https://pith.science/api/pith-number/APCY5ZPESIXO6E4MQDTOXAWAN3/graph.json","fetch_events":"https://pith.science/api/pith-number/APCY5ZPESIXO6E4MQDTOXAWAN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APCY5ZPESIXO6E4MQDTOXAWAN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APCY5ZPESIXO6E4MQDTOXAWAN3/action/storage_attestation","attest_author":"https://pith.science/pith/APCY5ZPESIXO6E4MQDTOXAWAN3/action/author_attestation","sign_citation":"https://pith.science/pith/APCY5ZPESIXO6E4MQDTOXAWAN3/action/citation_signature","submit_replication":"https://pith.science/pith/APCY5ZPESIXO6E4MQDTOXAWAN3/action/replication_record"}},"created_at":"2026-05-18T00:28:40.182370+00:00","updated_at":"2026-05-18T00:28:40.182370+00:00"}