{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:YL4LUJKPYQW7PTZYBZY3KTOHGW","short_pith_number":"pith:YL4LUJKP","schema_version":"1.0","canonical_sha256":"c2f8ba254fc42df7cf380e71b54dc7359e84f8f12ebb15b272a2f0cf89471ce6","source":{"kind":"arxiv","id":"1712.07495","version":2},"attestation_state":"computed","paper":{"title":"A Distributed Frank-Wolfe Framework for Learning Low-Rank Matrices with the Trace Norm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DC","authors_text":"Aur\\'elien Bellet, Patrick Gallinari, Wenjie Zheng","submitted_at":"2017-12-20T14:28:21Z","abstract_excerpt":"We consider the problem of learning a high-dimensional but low-rank matrix from a large-scale dataset distributed over several machines, where low-rankness is enforced by a convex trace norm constraint. We propose DFW-Trace, a distributed Frank-Wolfe algorithm which leverages the low-rank structure of its updates to achieve efficiency in time, memory and communication usage. The step at the heart of DFW-Trace is solved approximately using a distributed version of the power method. We provide a theoretical analysis of the convergence of DFW-Trace, showing that we can ensure sublinear convergenc"},"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":"1712.07495","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-12-20T14:28:21Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"3c1f7ec64c29b8094673f40dfdcd2c24f47b29227d70a680fef7b9f19ef56cb5","abstract_canon_sha256":"7513f10861918623fdd69ca5309a0d0b6d378a8e0788194cdc39e98db8379f60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:08.151386Z","signature_b64":"jS0s2elKulI5jr2fecB2GFIzfoLPcRgImAA+26SB0Rh1H3XnmP9h7X9SB6q05cQQf8U7anFHS6YyOMZ49GLmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2f8ba254fc42df7cf380e71b54dc7359e84f8f12ebb15b272a2f0cf89471ce6","last_reissued_at":"2026-05-18T00:16:08.150665Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:08.150665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Distributed Frank-Wolfe Framework for Learning Low-Rank Matrices with the Trace Norm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DC","authors_text":"Aur\\'elien Bellet, Patrick Gallinari, Wenjie Zheng","submitted_at":"2017-12-20T14:28:21Z","abstract_excerpt":"We consider the problem of learning a high-dimensional but low-rank matrix from a large-scale dataset distributed over several machines, where low-rankness is enforced by a convex trace norm constraint. We propose DFW-Trace, a distributed Frank-Wolfe algorithm which leverages the low-rank structure of its updates to achieve efficiency in time, memory and communication usage. The step at the heart of DFW-Trace is solved approximately using a distributed version of the power method. We provide a theoretical analysis of the convergence of DFW-Trace, showing that we can ensure sublinear convergenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.07495","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":""},"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":"1712.07495","created_at":"2026-05-18T00:16:08.150784+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.07495v2","created_at":"2026-05-18T00:16:08.150784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.07495","created_at":"2026-05-18T00:16:08.150784+00:00"},{"alias_kind":"pith_short_12","alias_value":"YL4LUJKPYQW7","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"YL4LUJKPYQW7PTZY","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"YL4LUJKP","created_at":"2026-05-18T12:31:56.362134+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/YL4LUJKPYQW7PTZYBZY3KTOHGW","json":"https://pith.science/pith/YL4LUJKPYQW7PTZYBZY3KTOHGW.json","graph_json":"https://pith.science/api/pith-number/YL4LUJKPYQW7PTZYBZY3KTOHGW/graph.json","events_json":"https://pith.science/api/pith-number/YL4LUJKPYQW7PTZYBZY3KTOHGW/events.json","paper":"https://pith.science/paper/YL4LUJKP"},"agent_actions":{"view_html":"https://pith.science/pith/YL4LUJKPYQW7PTZYBZY3KTOHGW","download_json":"https://pith.science/pith/YL4LUJKPYQW7PTZYBZY3KTOHGW.json","view_paper":"https://pith.science/paper/YL4LUJKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.07495&json=true","fetch_graph":"https://pith.science/api/pith-number/YL4LUJKPYQW7PTZYBZY3KTOHGW/graph.json","fetch_events":"https://pith.science/api/pith-number/YL4LUJKPYQW7PTZYBZY3KTOHGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YL4LUJKPYQW7PTZYBZY3KTOHGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YL4LUJKPYQW7PTZYBZY3KTOHGW/action/storage_attestation","attest_author":"https://pith.science/pith/YL4LUJKPYQW7PTZYBZY3KTOHGW/action/author_attestation","sign_citation":"https://pith.science/pith/YL4LUJKPYQW7PTZYBZY3KTOHGW/action/citation_signature","submit_replication":"https://pith.science/pith/YL4LUJKPYQW7PTZYBZY3KTOHGW/action/replication_record"}},"created_at":"2026-05-18T00:16:08.150784+00:00","updated_at":"2026-05-18T00:16:08.150784+00:00"}