{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:74YAVYWJLM3CXBCVYZX77Z6D6C","short_pith_number":"pith:74YAVYWJ","schema_version":"1.0","canonical_sha256":"ff300ae2c95b362b8455c66fffe7c3f0b51b3cb9eb041ca25e6c0f215de842ab","source":{"kind":"arxiv","id":"1612.08461","version":2},"attestation_state":"computed","paper":{"title":"Randomized Block Frank-Wolfe for Convergent Large-Scale Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.OC","authors_text":"Daniel Romero, Gang Wang, Georgios B. Giannakis, Liang Zhang","submitted_at":"2016-12-27T00:01:13Z","abstract_excerpt":"Owing to their low-complexity iterations, Frank-Wolfe (FW) solvers are well suited for various large-scale learning tasks. When block-separable constraints are present, randomized block FW (RB-FW) has been shown to further reduce complexity by updating only a fraction of coordinate blocks per iteration. To circumvent the limitations of existing methods, the present work develops step sizes for RB-FW that enable a flexible selection of the number of blocks to update per iteration while ensuring convergence and feasibility of the iterates. To this end, convergence rates of RB-FW are established "},"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":"1612.08461","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-12-27T00:01:13Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"8a4cfb6961129ef1f448dc94dfa8217b79882d74797774a772269c74dd7e2424","abstract_canon_sha256":"692920e2372da9ee9c4f8bf96b006aac489c56e1a27a0958c466c6f8422d679d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:06.085394Z","signature_b64":"IZLx7lKPYF6tQoANaLYKhLGpNqTfmg9TipnsewOMmySSpJACUx0jDFrFZlU5/CJL8qTw5Gv/T10kPcW3TYW2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff300ae2c95b362b8455c66fffe7c3f0b51b3cb9eb041ca25e6c0f215de842ab","last_reissued_at":"2026-05-18T00:30:06.084922Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:06.084922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Randomized Block Frank-Wolfe for Convergent Large-Scale Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.OC","authors_text":"Daniel Romero, Gang Wang, Georgios B. Giannakis, Liang Zhang","submitted_at":"2016-12-27T00:01:13Z","abstract_excerpt":"Owing to their low-complexity iterations, Frank-Wolfe (FW) solvers are well suited for various large-scale learning tasks. When block-separable constraints are present, randomized block FW (RB-FW) has been shown to further reduce complexity by updating only a fraction of coordinate blocks per iteration. To circumvent the limitations of existing methods, the present work develops step sizes for RB-FW that enable a flexible selection of the number of blocks to update per iteration while ensuring convergence and feasibility of the iterates. To this end, convergence rates of RB-FW are established "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.08461","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":"1612.08461","created_at":"2026-05-18T00:30:06.084994+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.08461v2","created_at":"2026-05-18T00:30:06.084994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.08461","created_at":"2026-05-18T00:30:06.084994+00:00"},{"alias_kind":"pith_short_12","alias_value":"74YAVYWJLM3C","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"74YAVYWJLM3CXBCV","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"74YAVYWJ","created_at":"2026-05-18T12:30:04.600751+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/74YAVYWJLM3CXBCVYZX77Z6D6C","json":"https://pith.science/pith/74YAVYWJLM3CXBCVYZX77Z6D6C.json","graph_json":"https://pith.science/api/pith-number/74YAVYWJLM3CXBCVYZX77Z6D6C/graph.json","events_json":"https://pith.science/api/pith-number/74YAVYWJLM3CXBCVYZX77Z6D6C/events.json","paper":"https://pith.science/paper/74YAVYWJ"},"agent_actions":{"view_html":"https://pith.science/pith/74YAVYWJLM3CXBCVYZX77Z6D6C","download_json":"https://pith.science/pith/74YAVYWJLM3CXBCVYZX77Z6D6C.json","view_paper":"https://pith.science/paper/74YAVYWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.08461&json=true","fetch_graph":"https://pith.science/api/pith-number/74YAVYWJLM3CXBCVYZX77Z6D6C/graph.json","fetch_events":"https://pith.science/api/pith-number/74YAVYWJLM3CXBCVYZX77Z6D6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74YAVYWJLM3CXBCVYZX77Z6D6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74YAVYWJLM3CXBCVYZX77Z6D6C/action/storage_attestation","attest_author":"https://pith.science/pith/74YAVYWJLM3CXBCVYZX77Z6D6C/action/author_attestation","sign_citation":"https://pith.science/pith/74YAVYWJLM3CXBCVYZX77Z6D6C/action/citation_signature","submit_replication":"https://pith.science/pith/74YAVYWJLM3CXBCVYZX77Z6D6C/action/replication_record"}},"created_at":"2026-05-18T00:30:06.084994+00:00","updated_at":"2026-05-18T00:30:06.084994+00:00"}