{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HIF4S6HRUADR2HIX635M6LAH3O","short_pith_number":"pith:HIF4S6HR","schema_version":"1.0","canonical_sha256":"3a0bc978f1a0071d1d17f6facf2c07dbb8720c788c5b10338abf7cb73651190a","source":{"kind":"arxiv","id":"2304.11737","version":2},"attestation_state":"computed","paper":{"title":"Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Aleksandr Beznosikov, David Dobre, Gauthier Gidel","submitted_at":"2023-04-23T20:05:09Z","abstract_excerpt":"The Frank-Wolfe (FW) method is a popular approach for solving optimization problems with structured constraints that arise in machine learning applications. In recent years, stochastic versions of FW have gained popularity, motivated by large datasets for which the computation of the full gradient is prohibitively expensive. In this paper, we present two new variants of the FW algorithms for stochastic finite-sum minimization. Our algorithms have the best convergence guarantees of existing stochastic FW approaches for both convex and non-convex objective functions. Our methods do not have the "},"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":"2304.11737","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-04-23T20:05:09Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"86e5a35fc669db90198f625440017b78cbe9cc54c79458fc0a065bb3c9e8e4d6","abstract_canon_sha256":"e0eacb56c705d6a079ae9f4f9107dc7f5cf2a86f19cd05ce8a6f9e4d1ebbffc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:53.656941Z","signature_b64":"tz97oAz5h3+3JpbnfnovDH/GLAGG4ZX4R47lwRmoPJ/aIrYZJt4ZY4J0oP6K+5iYqEVyCe5fVgRC0UUZEs7jCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a0bc978f1a0071d1d17f6facf2c07dbb8720c788c5b10338abf7cb73651190a","last_reissued_at":"2026-07-05T09:06:53.656466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:53.656466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Aleksandr Beznosikov, David Dobre, Gauthier Gidel","submitted_at":"2023-04-23T20:05:09Z","abstract_excerpt":"The Frank-Wolfe (FW) method is a popular approach for solving optimization problems with structured constraints that arise in machine learning applications. In recent years, stochastic versions of FW have gained popularity, motivated by large datasets for which the computation of the full gradient is prohibitively expensive. In this paper, we present two new variants of the FW algorithms for stochastic finite-sum minimization. Our algorithms have the best convergence guarantees of existing stochastic FW approaches for both convex and non-convex objective functions. Our methods do not have the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11737","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/2304.11737/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":"2304.11737","created_at":"2026-07-05T09:06:53.656526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.11737v2","created_at":"2026-07-05T09:06:53.656526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11737","created_at":"2026-07-05T09:06:53.656526+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIF4S6HRUADR","created_at":"2026-07-05T09:06:53.656526+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIF4S6HRUADR2HIX","created_at":"2026-07-05T09:06:53.656526+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIF4S6HR","created_at":"2026-07-05T09:06:53.656526+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25255","citing_title":"Boosted Stochastic Frank-Wolfe for Constrained Nonconvex Optimization","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HIF4S6HRUADR2HIX635M6LAH3O","json":"https://pith.science/pith/HIF4S6HRUADR2HIX635M6LAH3O.json","graph_json":"https://pith.science/api/pith-number/HIF4S6HRUADR2HIX635M6LAH3O/graph.json","events_json":"https://pith.science/api/pith-number/HIF4S6HRUADR2HIX635M6LAH3O/events.json","paper":"https://pith.science/paper/HIF4S6HR"},"agent_actions":{"view_html":"https://pith.science/pith/HIF4S6HRUADR2HIX635M6LAH3O","download_json":"https://pith.science/pith/HIF4S6HRUADR2HIX635M6LAH3O.json","view_paper":"https://pith.science/paper/HIF4S6HR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.11737&json=true","fetch_graph":"https://pith.science/api/pith-number/HIF4S6HRUADR2HIX635M6LAH3O/graph.json","fetch_events":"https://pith.science/api/pith-number/HIF4S6HRUADR2HIX635M6LAH3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIF4S6HRUADR2HIX635M6LAH3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIF4S6HRUADR2HIX635M6LAH3O/action/storage_attestation","attest_author":"https://pith.science/pith/HIF4S6HRUADR2HIX635M6LAH3O/action/author_attestation","sign_citation":"https://pith.science/pith/HIF4S6HRUADR2HIX635M6LAH3O/action/citation_signature","submit_replication":"https://pith.science/pith/HIF4S6HRUADR2HIX635M6LAH3O/action/replication_record"}},"created_at":"2026-07-05T09:06:53.656526+00:00","updated_at":"2026-07-05T09:06:53.656526+00:00"}