{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LWYU37JTYLONDJ4VK5JFBIGNWW","short_pith_number":"pith:LWYU37JT","schema_version":"1.0","canonical_sha256":"5db14dfd33c2dcd1a795575250a0cdb5a1bada5636958cbd51694ab755b15e78","source":{"kind":"arxiv","id":"1712.01033","version":2},"attestation_state":"computed","paper":{"title":"NEON+: Accelerated Gradient Methods for Extracting Negative Curvature for Non-Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Rong Jin, Tianbao Yang, Yi Xu","submitted_at":"2017-12-04T12:17:19Z","abstract_excerpt":"Accelerated gradient (AG) methods are breakthroughs in convex optimization, improving the convergence rate of the gradient descent method for optimization with smooth functions. However, the analysis of AG methods for non-convex optimization is still limited. It remains an open question whether AG methods from convex optimization can accelerate the convergence of the gradient descent method for finding local minimum of non-convex optimization problems. This paper provides an affirmative answer to this question. In particular, we analyze two renowned variants of AG methods (namely Polyak's Heav"},"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":"1712.01033","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-12-04T12:17:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"17c7203097cd710a29d928a776f5607438baa74afd9a51d404ec3797d042dfc0","abstract_canon_sha256":"da756df1d617069569bbfa520682c0087206c210f0117ba0be215f2fc07153a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:10.513752Z","signature_b64":"F1fYSMbs1fLtyt98pctSByOITTLJXpwrUz3bhNrGVuhqB8Q0V/wer0X/O+bTZAmtxe1DhymO22LAPWJTFfX1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5db14dfd33c2dcd1a795575250a0cdb5a1bada5636958cbd51694ab755b15e78","last_reissued_at":"2026-05-18T00:22:10.513216Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:10.513216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NEON+: Accelerated Gradient Methods for Extracting Negative Curvature for Non-Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Rong Jin, Tianbao Yang, Yi Xu","submitted_at":"2017-12-04T12:17:19Z","abstract_excerpt":"Accelerated gradient (AG) methods are breakthroughs in convex optimization, improving the convergence rate of the gradient descent method for optimization with smooth functions. However, the analysis of AG methods for non-convex optimization is still limited. It remains an open question whether AG methods from convex optimization can accelerate the convergence of the gradient descent method for finding local minimum of non-convex optimization problems. This paper provides an affirmative answer to this question. In particular, we analyze two renowned variants of AG methods (namely Polyak's Heav"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01033","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":"1712.01033","created_at":"2026-05-18T00:22:10.513299+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.01033v2","created_at":"2026-05-18T00:22:10.513299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01033","created_at":"2026-05-18T00:22:10.513299+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWYU37JTYLON","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWYU37JTYLONDJ4V","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWYU37JT","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24488","citing_title":"Scalable First-Order Interior Point Trust Region Algorithms for Linearly Constrained Optimization","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWYU37JTYLONDJ4VK5JFBIGNWW","json":"https://pith.science/pith/LWYU37JTYLONDJ4VK5JFBIGNWW.json","graph_json":"https://pith.science/api/pith-number/LWYU37JTYLONDJ4VK5JFBIGNWW/graph.json","events_json":"https://pith.science/api/pith-number/LWYU37JTYLONDJ4VK5JFBIGNWW/events.json","paper":"https://pith.science/paper/LWYU37JT"},"agent_actions":{"view_html":"https://pith.science/pith/LWYU37JTYLONDJ4VK5JFBIGNWW","download_json":"https://pith.science/pith/LWYU37JTYLONDJ4VK5JFBIGNWW.json","view_paper":"https://pith.science/paper/LWYU37JT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.01033&json=true","fetch_graph":"https://pith.science/api/pith-number/LWYU37JTYLONDJ4VK5JFBIGNWW/graph.json","fetch_events":"https://pith.science/api/pith-number/LWYU37JTYLONDJ4VK5JFBIGNWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWYU37JTYLONDJ4VK5JFBIGNWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWYU37JTYLONDJ4VK5JFBIGNWW/action/storage_attestation","attest_author":"https://pith.science/pith/LWYU37JTYLONDJ4VK5JFBIGNWW/action/author_attestation","sign_citation":"https://pith.science/pith/LWYU37JTYLONDJ4VK5JFBIGNWW/action/citation_signature","submit_replication":"https://pith.science/pith/LWYU37JTYLONDJ4VK5JFBIGNWW/action/replication_record"}},"created_at":"2026-05-18T00:22:10.513299+00:00","updated_at":"2026-05-18T00:22:10.513299+00:00"}