{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VQL66LSB46EBVABYCLOS6UDRSW","short_pith_number":"pith:VQL66LSB","schema_version":"1.0","canonical_sha256":"ac17ef2e41e7881a803812dd2f50719587690d093b0ede53c35e25e5238b6315","source":{"kind":"arxiv","id":"1711.06673","version":3},"attestation_state":"computed","paper":{"title":"Neon2: Finding Local Minima via First-Order Oracles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Yuanzhi Li, Zeyuan Allen-Zhu","submitted_at":"2017-11-17T18:59:01Z","abstract_excerpt":"We propose a reduction for non-convex optimization that can (1) turn an stationary-point finding algorithm into an local-minimum finding one, and (2) replace the Hessian-vector product computations with only gradient computations. It works both in the stochastic and the deterministic settings, without hurting the algorithm's performance.\n  As applications, our reduction turns Natasha2 into a first-order method without hurting its performance. It also converts SGD, GD, SCSG, and SVRG into algorithms finding approximate local minima, outperforming some best known results."},"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":"1711.06673","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-17T18:59:01Z","cross_cats_sorted":["cs.DS","cs.NE","math.OC","stat.ML"],"title_canon_sha256":"64c027f327495d9bfafc19bcc0233ed928bfd1318059f4ec0f355889340c8f86","abstract_canon_sha256":"2524edb92ff46a110cf100483155a958c3e1aa177bd8a19fb2251e9a7a6d1377"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:59.828936Z","signature_b64":"wz4kAmi/SmSVA3RUCuBG8A3SBOM2lPn0h6rkSiLpJ9x3plVQPhINJQvpGVr8EBMQ2bB+1CAsCVJIeMHDCACSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac17ef2e41e7881a803812dd2f50719587690d093b0ede53c35e25e5238b6315","last_reissued_at":"2026-05-18T00:17:59.828341Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:59.828341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neon2: Finding Local Minima via First-Order Oracles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Yuanzhi Li, Zeyuan Allen-Zhu","submitted_at":"2017-11-17T18:59:01Z","abstract_excerpt":"We propose a reduction for non-convex optimization that can (1) turn an stationary-point finding algorithm into an local-minimum finding one, and (2) replace the Hessian-vector product computations with only gradient computations. It works both in the stochastic and the deterministic settings, without hurting the algorithm's performance.\n  As applications, our reduction turns Natasha2 into a first-order method without hurting its performance. It also converts SGD, GD, SCSG, and SVRG into algorithms finding approximate local minima, outperforming some best known results."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06673","kind":"arxiv","version":3},"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":"1711.06673","created_at":"2026-05-18T00:17:59.828439+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.06673v3","created_at":"2026-05-18T00:17:59.828439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06673","created_at":"2026-05-18T00:17:59.828439+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQL66LSB46EB","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQL66LSB46EBVABY","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQL66LSB","created_at":"2026-05-18T12:31:49.984773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2003.00295","citing_title":"Adaptive Federated Optimization","ref_index":177,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24488","citing_title":"Scalable First-Order Interior Point Trust Region Algorithms for Linearly Constrained Optimization","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQL66LSB46EBVABYCLOS6UDRSW","json":"https://pith.science/pith/VQL66LSB46EBVABYCLOS6UDRSW.json","graph_json":"https://pith.science/api/pith-number/VQL66LSB46EBVABYCLOS6UDRSW/graph.json","events_json":"https://pith.science/api/pith-number/VQL66LSB46EBVABYCLOS6UDRSW/events.json","paper":"https://pith.science/paper/VQL66LSB"},"agent_actions":{"view_html":"https://pith.science/pith/VQL66LSB46EBVABYCLOS6UDRSW","download_json":"https://pith.science/pith/VQL66LSB46EBVABYCLOS6UDRSW.json","view_paper":"https://pith.science/paper/VQL66LSB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.06673&json=true","fetch_graph":"https://pith.science/api/pith-number/VQL66LSB46EBVABYCLOS6UDRSW/graph.json","fetch_events":"https://pith.science/api/pith-number/VQL66LSB46EBVABYCLOS6UDRSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQL66LSB46EBVABYCLOS6UDRSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQL66LSB46EBVABYCLOS6UDRSW/action/storage_attestation","attest_author":"https://pith.science/pith/VQL66LSB46EBVABYCLOS6UDRSW/action/author_attestation","sign_citation":"https://pith.science/pith/VQL66LSB46EBVABYCLOS6UDRSW/action/citation_signature","submit_replication":"https://pith.science/pith/VQL66LSB46EBVABYCLOS6UDRSW/action/replication_record"}},"created_at":"2026-05-18T00:17:59.828439+00:00","updated_at":"2026-05-18T00:17:59.828439+00:00"}