{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:USTRB4CLVVKSKLCDZ7F6OBTSNQ","short_pith_number":"pith:USTRB4CL","schema_version":"1.0","canonical_sha256":"a4a710f04bad55252c43cfcbe706726c3c767e7535223f381b7ea4b6155f6d92","source":{"kind":"arxiv","id":"2408.10090","version":1},"attestation_state":"computed","paper":{"title":"Federated Frank-Wolfe Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Ali Dadras, Alp Yurtsever, Karthik Prakhya, Sourasekhar Banerjee","submitted_at":"2024-08-19T15:31:06Z","abstract_excerpt":"Federated learning (FL) has gained a lot of attention in recent years for building privacy-preserving collaborative learning systems. However, FL algorithms for constrained machine learning problems are still limited, particularly when the projection step is costly. To this end, we propose a Federated Frank-Wolfe Algorithm (FedFW). FedFW features data privacy, low per-iteration cost, and communication of sparse signals. In the deterministic setting, FedFW achieves an $\\varepsilon$-suboptimal solution within $O(\\varepsilon^{-2})$ iterations for smooth and convex objectives, and $O(\\varepsilon^{"},"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":"2408.10090","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T15:31:06Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"5b698a4b3ec972934c816a51f45e5feddc07e8a9c1752119bd15237791180f45","abstract_canon_sha256":"20a076a6ef1eb5805a1ccd3ded8c58ab0f10db3b2f9f21cc94cdfc9fe2d005e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:51.246478Z","signature_b64":"k7W5oSkZQPCIF8zU+IPvLuf94dkvEbmNuumXsztLwQt2IJj7YGlF71Ppb6E0l5qoi1lh8xf0O/5rT9xsE+G9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4a710f04bad55252c43cfcbe706726c3c767e7535223f381b7ea4b6155f6d92","last_reissued_at":"2026-07-05T08:56:51.246064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:51.246064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Frank-Wolfe Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Ali Dadras, Alp Yurtsever, Karthik Prakhya, Sourasekhar Banerjee","submitted_at":"2024-08-19T15:31:06Z","abstract_excerpt":"Federated learning (FL) has gained a lot of attention in recent years for building privacy-preserving collaborative learning systems. However, FL algorithms for constrained machine learning problems are still limited, particularly when the projection step is costly. To this end, we propose a Federated Frank-Wolfe Algorithm (FedFW). FedFW features data privacy, low per-iteration cost, and communication of sparse signals. In the deterministic setting, FedFW achieves an $\\varepsilon$-suboptimal solution within $O(\\varepsilon^{-2})$ iterations for smooth and convex objectives, and $O(\\varepsilon^{"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10090","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/2408.10090/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":"2408.10090","created_at":"2026-07-05T08:56:51.246124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10090v1","created_at":"2026-07-05T08:56:51.246124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10090","created_at":"2026-07-05T08:56:51.246124+00:00"},{"alias_kind":"pith_short_12","alias_value":"USTRB4CLVVKS","created_at":"2026-07-05T08:56:51.246124+00:00"},{"alias_kind":"pith_short_16","alias_value":"USTRB4CLVVKSKLCD","created_at":"2026-07-05T08:56:51.246124+00:00"},{"alias_kind":"pith_short_8","alias_value":"USTRB4CL","created_at":"2026-07-05T08:56:51.246124+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/USTRB4CLVVKSKLCDZ7F6OBTSNQ","json":"https://pith.science/pith/USTRB4CLVVKSKLCDZ7F6OBTSNQ.json","graph_json":"https://pith.science/api/pith-number/USTRB4CLVVKSKLCDZ7F6OBTSNQ/graph.json","events_json":"https://pith.science/api/pith-number/USTRB4CLVVKSKLCDZ7F6OBTSNQ/events.json","paper":"https://pith.science/paper/USTRB4CL"},"agent_actions":{"view_html":"https://pith.science/pith/USTRB4CLVVKSKLCDZ7F6OBTSNQ","download_json":"https://pith.science/pith/USTRB4CLVVKSKLCDZ7F6OBTSNQ.json","view_paper":"https://pith.science/paper/USTRB4CL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10090&json=true","fetch_graph":"https://pith.science/api/pith-number/USTRB4CLVVKSKLCDZ7F6OBTSNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/USTRB4CLVVKSKLCDZ7F6OBTSNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/USTRB4CLVVKSKLCDZ7F6OBTSNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/USTRB4CLVVKSKLCDZ7F6OBTSNQ/action/storage_attestation","attest_author":"https://pith.science/pith/USTRB4CLVVKSKLCDZ7F6OBTSNQ/action/author_attestation","sign_citation":"https://pith.science/pith/USTRB4CLVVKSKLCDZ7F6OBTSNQ/action/citation_signature","submit_replication":"https://pith.science/pith/USTRB4CLVVKSKLCDZ7F6OBTSNQ/action/replication_record"}},"created_at":"2026-07-05T08:56:51.246124+00:00","updated_at":"2026-07-05T08:56:51.246124+00:00"}