{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:QGLVIER7L6DDYU7Z6ZN67R3Y3X","short_pith_number":"pith:QGLVIER7","schema_version":"1.0","canonical_sha256":"819754123f5f863c53f9f65befc778ddd8e1cd9dfd5c60fa4cc86dc6064c306a","source":{"kind":"arxiv","id":"1607.00345","version":1},"attestation_state":"computed","paper":{"title":"Convergence Rate of Frank-Wolfe for Non-Convex Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Simon Lacoste-Julien","submitted_at":"2016-07-01T18:37:33Z","abstract_excerpt":"We give a simple proof that the Frank-Wolfe algorithm obtains a stationary point at a rate of $O(1/\\sqrt{t})$ on non-convex objectives with a Lipschitz continuous gradient. Our analysis is affine invariant and is the first, to the best of our knowledge, giving a similar rate to what was already proven for projected gradient methods (though on slightly different measures of stationarity)."},"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":"1607.00345","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-07-01T18:37:33Z","cross_cats_sorted":["cs.LG","cs.NA","stat.ML"],"title_canon_sha256":"7a741bff16c3e8904aae80653f04a5b0ae7335f2886ead10690aee5e2b464d54","abstract_canon_sha256":"a5b9becedcc584bec99c46f382078fbe584fd3a52275460cafca83270c985ee3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:26.528711Z","signature_b64":"xZWB+amjW1oHwxbucGwNUPiwk+3eN+OFU6FFvoioXgwaKXfJS9PoS2OsTzKyX1yJ3yIlUil6wCd5bWY+DV5kCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"819754123f5f863c53f9f65befc778ddd8e1cd9dfd5c60fa4cc86dc6064c306a","last_reissued_at":"2026-05-18T01:11:26.528025Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:26.528025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence Rate of Frank-Wolfe for Non-Convex Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Simon Lacoste-Julien","submitted_at":"2016-07-01T18:37:33Z","abstract_excerpt":"We give a simple proof that the Frank-Wolfe algorithm obtains a stationary point at a rate of $O(1/\\sqrt{t})$ on non-convex objectives with a Lipschitz continuous gradient. Our analysis is affine invariant and is the first, to the best of our knowledge, giving a similar rate to what was already proven for projected gradient methods (though on slightly different measures of stationarity)."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.00345","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":""},"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":"1607.00345","created_at":"2026-05-18T01:11:26.528139+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.00345v1","created_at":"2026-05-18T01:11:26.528139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.00345","created_at":"2026-05-18T01:11:26.528139+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGLVIER7L6DD","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGLVIER7L6DDYU7Z","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGLVIER7","created_at":"2026-05-18T12:30:39.010887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2606.18650","citing_title":"BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30337","citing_title":"Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30807","citing_title":"Conformal Reliability: A New Evaluation Metric for Conditional Generation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11580","citing_title":"Gradient projection and conditional gradient methods for constrained nonconvex minimization","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00312","citing_title":"Competitive Algorithms for Online Budget-Constrained Continuous DR-Submodular Problems","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12161","citing_title":"Fused Gromov-Wasserstein Distance with Feature Selection","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24488","citing_title":"Scalable First-Order Interior Point Trust Region Algorithms for Linearly Constrained Optimization","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05577","citing_title":"Accelerating LMO-Based Optimization via Implicit Gradient Transport","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01580","citing_title":"Model Merging: Foundations and Algorithms","ref_index":100,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QGLVIER7L6DDYU7Z6ZN67R3Y3X","json":"https://pith.science/pith/QGLVIER7L6DDYU7Z6ZN67R3Y3X.json","graph_json":"https://pith.science/api/pith-number/QGLVIER7L6DDYU7Z6ZN67R3Y3X/graph.json","events_json":"https://pith.science/api/pith-number/QGLVIER7L6DDYU7Z6ZN67R3Y3X/events.json","paper":"https://pith.science/paper/QGLVIER7"},"agent_actions":{"view_html":"https://pith.science/pith/QGLVIER7L6DDYU7Z6ZN67R3Y3X","download_json":"https://pith.science/pith/QGLVIER7L6DDYU7Z6ZN67R3Y3X.json","view_paper":"https://pith.science/paper/QGLVIER7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.00345&json=true","fetch_graph":"https://pith.science/api/pith-number/QGLVIER7L6DDYU7Z6ZN67R3Y3X/graph.json","fetch_events":"https://pith.science/api/pith-number/QGLVIER7L6DDYU7Z6ZN67R3Y3X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGLVIER7L6DDYU7Z6ZN67R3Y3X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGLVIER7L6DDYU7Z6ZN67R3Y3X/action/storage_attestation","attest_author":"https://pith.science/pith/QGLVIER7L6DDYU7Z6ZN67R3Y3X/action/author_attestation","sign_citation":"https://pith.science/pith/QGLVIER7L6DDYU7Z6ZN67R3Y3X/action/citation_signature","submit_replication":"https://pith.science/pith/QGLVIER7L6DDYU7Z6ZN67R3Y3X/action/replication_record"}},"created_at":"2026-05-18T01:11:26.528139+00:00","updated_at":"2026-05-18T01:11:26.528139+00:00"}