{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KIFXCRWZQYABW5AYSP4NHK4VRQ","short_pith_number":"pith:KIFXCRWZ","schema_version":"1.0","canonical_sha256":"520b7146d986001b741893f8d3ab958c2eb0a9be0ecca60dfb1b2954706ef828","source":{"kind":"arxiv","id":"2008.02252","version":2},"attestation_state":"computed","paper":{"title":"An accelerated first-order method for non-convex optimization on manifolds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.DG","math.NA"],"primary_cat":"math.OC","authors_text":"Christopher Criscitiello, Nicolas Boumal","submitted_at":"2020-08-05T17:30:35Z","abstract_excerpt":"We describe the first gradient methods on Riemannian manifolds to achieve accelerated rates in the non-convex case. Under Lipschitz assumptions on the Riemannian gradient and Hessian of the cost function, these methods find approximate first-order critical points faster than regular gradient descent. A randomized version also finds approximate second-order critical points. Both the algorithms and their analyses build extensively on existing work in the Euclidean case. The basic operation consists in running the Euclidean accelerated gradient descent method (appropriately safe-guarded against n"},"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":"2008.02252","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-08-05T17:30:35Z","cross_cats_sorted":["cs.NA","math.DG","math.NA"],"title_canon_sha256":"3e67a4d6609fdb1ff0dddf839937b31d600ce4eeb7b034c72c2e8aa7181b443c","abstract_canon_sha256":"f4d95df95ef1ebcc637aa664c146ca6c3d173c3ee653ff72e5e17727a53bc851"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:06.690404Z","signature_b64":"Gi4eQTDbglEfbvxv+BG6IV1SKihza4whbfTiAE+mGabXa4teG+j4h2xkzQBl0BXoDxgjX0xFG/d9kLoJVXjpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"520b7146d986001b741893f8d3ab958c2eb0a9be0ecca60dfb1b2954706ef828","last_reissued_at":"2026-07-05T03:35:06.689905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:06.689905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An accelerated first-order method for non-convex optimization on manifolds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.DG","math.NA"],"primary_cat":"math.OC","authors_text":"Christopher Criscitiello, Nicolas Boumal","submitted_at":"2020-08-05T17:30:35Z","abstract_excerpt":"We describe the first gradient methods on Riemannian manifolds to achieve accelerated rates in the non-convex case. Under Lipschitz assumptions on the Riemannian gradient and Hessian of the cost function, these methods find approximate first-order critical points faster than regular gradient descent. A randomized version also finds approximate second-order critical points. Both the algorithms and their analyses build extensively on existing work in the Euclidean case. The basic operation consists in running the Euclidean accelerated gradient descent method (appropriately safe-guarded against n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02252","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/2008.02252/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":"2008.02252","created_at":"2026-07-05T03:35:06.689962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.02252v2","created_at":"2026-07-05T03:35:06.689962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02252","created_at":"2026-07-05T03:35:06.689962+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIFXCRWZQYAB","created_at":"2026-07-05T03:35:06.689962+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIFXCRWZQYABW5AY","created_at":"2026-07-05T03:35:06.689962+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIFXCRWZ","created_at":"2026-07-05T03:35:06.689962+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16055","citing_title":"The Intrinsic Riemannian Proximal Gradient Method for Convex Optimization","ref_index":319,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KIFXCRWZQYABW5AYSP4NHK4VRQ","json":"https://pith.science/pith/KIFXCRWZQYABW5AYSP4NHK4VRQ.json","graph_json":"https://pith.science/api/pith-number/KIFXCRWZQYABW5AYSP4NHK4VRQ/graph.json","events_json":"https://pith.science/api/pith-number/KIFXCRWZQYABW5AYSP4NHK4VRQ/events.json","paper":"https://pith.science/paper/KIFXCRWZ"},"agent_actions":{"view_html":"https://pith.science/pith/KIFXCRWZQYABW5AYSP4NHK4VRQ","download_json":"https://pith.science/pith/KIFXCRWZQYABW5AYSP4NHK4VRQ.json","view_paper":"https://pith.science/paper/KIFXCRWZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.02252&json=true","fetch_graph":"https://pith.science/api/pith-number/KIFXCRWZQYABW5AYSP4NHK4VRQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KIFXCRWZQYABW5AYSP4NHK4VRQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIFXCRWZQYABW5AYSP4NHK4VRQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIFXCRWZQYABW5AYSP4NHK4VRQ/action/storage_attestation","attest_author":"https://pith.science/pith/KIFXCRWZQYABW5AYSP4NHK4VRQ/action/author_attestation","sign_citation":"https://pith.science/pith/KIFXCRWZQYABW5AYSP4NHK4VRQ/action/citation_signature","submit_replication":"https://pith.science/pith/KIFXCRWZQYABW5AYSP4NHK4VRQ/action/replication_record"}},"created_at":"2026-07-05T03:35:06.689962+00:00","updated_at":"2026-07-05T03:35:06.689962+00:00"}