{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RQPCDGL376TVAQFSVXKLJDO5D5","short_pith_number":"pith:RQPCDGL3","schema_version":"1.0","canonical_sha256":"8c1e21997bffa75040b2add4b48ddd1f653747a9556635ffc5b593fd1b2fedcb","source":{"kind":"arxiv","id":"1605.06492","version":1},"attestation_state":"computed","paper":{"title":"Linear-memory and Decomposition-invariant Linearly Convergent Conditional Gradient Algorithm for Structured Polytopes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Dan Garber, Ofer Meshi","submitted_at":"2016-05-20T19:55:48Z","abstract_excerpt":"Recently, several works have shown that natural modifications of the classical conditional gradient method (aka Frank-Wolfe algorithm) for constrained convex optimization, provably converge with a linear rate when: i) the feasible set is a polytope, and ii) the objective is smooth and strongly-convex. However, all of these results suffer from two significant shortcomings: large memory requirement due to the need to store an explicit convex decomposition of the current iterate, and as a consequence, large running-time overhead per iteration, and worst case convergence rate that depends unfavora"},"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":"1605.06492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-05-20T19:55:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec3ae5479695c2aed9650b395b42efb981f9c5498a68b84f021d6d48598ec3ba","abstract_canon_sha256":"85360725b5b0fd0c6ffbfb55ac4089bace988b183d5689febcc4837d25d6e1f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:18.760291Z","signature_b64":"EiGa5yWlv4Y0XQOVIZdgK+1kqhRC/QAA8aZh18O9+jcJ1+aNUQIcA9luJWnPPTDqwYsSbtcXr8YvHsnn9THuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c1e21997bffa75040b2add4b48ddd1f653747a9556635ffc5b593fd1b2fedcb","last_reissued_at":"2026-05-18T01:14:18.759664Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:18.759664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linear-memory and Decomposition-invariant Linearly Convergent Conditional Gradient Algorithm for Structured Polytopes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Dan Garber, Ofer Meshi","submitted_at":"2016-05-20T19:55:48Z","abstract_excerpt":"Recently, several works have shown that natural modifications of the classical conditional gradient method (aka Frank-Wolfe algorithm) for constrained convex optimization, provably converge with a linear rate when: i) the feasible set is a polytope, and ii) the objective is smooth and strongly-convex. However, all of these results suffer from two significant shortcomings: large memory requirement due to the need to store an explicit convex decomposition of the current iterate, and as a consequence, large running-time overhead per iteration, and worst case convergence rate that depends unfavora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06492","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":"1605.06492","created_at":"2026-05-18T01:14:18.759751+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.06492v1","created_at":"2026-05-18T01:14:18.759751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06492","created_at":"2026-05-18T01:14:18.759751+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQPCDGL376TV","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQPCDGL376TVAQFS","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQPCDGL3","created_at":"2026-05-18T12:30:41.710351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQPCDGL376TVAQFSVXKLJDO5D5","json":"https://pith.science/pith/RQPCDGL376TVAQFSVXKLJDO5D5.json","graph_json":"https://pith.science/api/pith-number/RQPCDGL376TVAQFSVXKLJDO5D5/graph.json","events_json":"https://pith.science/api/pith-number/RQPCDGL376TVAQFSVXKLJDO5D5/events.json","paper":"https://pith.science/paper/RQPCDGL3"},"agent_actions":{"view_html":"https://pith.science/pith/RQPCDGL376TVAQFSVXKLJDO5D5","download_json":"https://pith.science/pith/RQPCDGL376TVAQFSVXKLJDO5D5.json","view_paper":"https://pith.science/paper/RQPCDGL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.06492&json=true","fetch_graph":"https://pith.science/api/pith-number/RQPCDGL376TVAQFSVXKLJDO5D5/graph.json","fetch_events":"https://pith.science/api/pith-number/RQPCDGL376TVAQFSVXKLJDO5D5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQPCDGL376TVAQFSVXKLJDO5D5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQPCDGL376TVAQFSVXKLJDO5D5/action/storage_attestation","attest_author":"https://pith.science/pith/RQPCDGL376TVAQFSVXKLJDO5D5/action/author_attestation","sign_citation":"https://pith.science/pith/RQPCDGL376TVAQFSVXKLJDO5D5/action/citation_signature","submit_replication":"https://pith.science/pith/RQPCDGL376TVAQFSVXKLJDO5D5/action/replication_record"}},"created_at":"2026-05-18T01:14:18.759751+00:00","updated_at":"2026-05-18T01:14:18.759751+00:00"}