{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MDEYEIDRLIMMVXHBOMQWOVNKVS","short_pith_number":"pith:MDEYEIDR","schema_version":"1.0","canonical_sha256":"60c98220715a18cadce173216755aaac9251d3f66954d1c72c3db380f01cc85f","source":{"kind":"arxiv","id":"2606.05438","version":1},"attestation_state":"computed","paper":{"title":"Sharp First-Order Lower Bounds for Higher-Order Smooth Nonconvex Optimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou","submitted_at":"2026-06-03T21:01:21Z","abstract_excerpt":"We study the deterministic first-order oracle complexity of finding \\(\\epsilon\\)-stationary points in smooth nonconvex optimization when the objective satisfies higher-order smoothness assumptions. While the classical \\(\\epsilon^{-2}\\) rate is optimal under only Lipschitz gradients, higher-order smoothness leads to accelerated first-order upper bounds, most notably the \\(\\epsilon^{-7/4}\\) rate under Lipschitz Hessians and the \\(\\epsilon^{-5/3}\\) rate under Lipschitz third derivatives. The matching lower bounds, however, have remained open. We resolve this gap by proving a new dimension-free fi"},"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":"2606.05438","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T21:01:21Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"92cb4118bdff1fedb90028a6549afbae343d7e563d85b0183c82be95b71f6fbc","abstract_canon_sha256":"ffbba0366d0938a508ab2fc098157a86e43f93c3bddbefa51e27ef3f80e86696"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:57.889909Z","signature_b64":"A/+VQ5LSm5XpcVxFfOfZea4zxqr6ju0qBDNMyHbKNLfC6DTeukjGv5qwKo8ExJJZxvcs2vOpCZ10hiZ1n9O6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60c98220715a18cadce173216755aaac9251d3f66954d1c72c3db380f01cc85f","last_reissued_at":"2026-06-05T00:13:57.889479Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:57.889479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sharp First-Order Lower Bounds for Higher-Order Smooth Nonconvex Optimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou","submitted_at":"2026-06-03T21:01:21Z","abstract_excerpt":"We study the deterministic first-order oracle complexity of finding \\(\\epsilon\\)-stationary points in smooth nonconvex optimization when the objective satisfies higher-order smoothness assumptions. While the classical \\(\\epsilon^{-2}\\) rate is optimal under only Lipschitz gradients, higher-order smoothness leads to accelerated first-order upper bounds, most notably the \\(\\epsilon^{-7/4}\\) rate under Lipschitz Hessians and the \\(\\epsilon^{-5/3}\\) rate under Lipschitz third derivatives. The matching lower bounds, however, have remained open. We resolve this gap by proving a new dimension-free fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05438","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/2606.05438/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":"2606.05438","created_at":"2026-06-05T00:13:57.889539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05438v1","created_at":"2026-06-05T00:13:57.889539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05438","created_at":"2026-06-05T00:13:57.889539+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDEYEIDRLIMM","created_at":"2026-06-05T00:13:57.889539+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDEYEIDRLIMMVXHB","created_at":"2026-06-05T00:13:57.889539+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDEYEIDR","created_at":"2026-06-05T00:13:57.889539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.30050","citing_title":"A Restart-Free Accelerated Algorithm for Non-Convex Minimization: Continuous and Discrete Analysis","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDEYEIDRLIMMVXHBOMQWOVNKVS","json":"https://pith.science/pith/MDEYEIDRLIMMVXHBOMQWOVNKVS.json","graph_json":"https://pith.science/api/pith-number/MDEYEIDRLIMMVXHBOMQWOVNKVS/graph.json","events_json":"https://pith.science/api/pith-number/MDEYEIDRLIMMVXHBOMQWOVNKVS/events.json","paper":"https://pith.science/paper/MDEYEIDR"},"agent_actions":{"view_html":"https://pith.science/pith/MDEYEIDRLIMMVXHBOMQWOVNKVS","download_json":"https://pith.science/pith/MDEYEIDRLIMMVXHBOMQWOVNKVS.json","view_paper":"https://pith.science/paper/MDEYEIDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05438&json=true","fetch_graph":"https://pith.science/api/pith-number/MDEYEIDRLIMMVXHBOMQWOVNKVS/graph.json","fetch_events":"https://pith.science/api/pith-number/MDEYEIDRLIMMVXHBOMQWOVNKVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDEYEIDRLIMMVXHBOMQWOVNKVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDEYEIDRLIMMVXHBOMQWOVNKVS/action/storage_attestation","attest_author":"https://pith.science/pith/MDEYEIDRLIMMVXHBOMQWOVNKVS/action/author_attestation","sign_citation":"https://pith.science/pith/MDEYEIDRLIMMVXHBOMQWOVNKVS/action/citation_signature","submit_replication":"https://pith.science/pith/MDEYEIDRLIMMVXHBOMQWOVNKVS/action/replication_record"}},"created_at":"2026-06-05T00:13:57.889539+00:00","updated_at":"2026-06-05T00:13:57.889539+00:00"}