{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ZOKIQFHCBMCAQVEY76L6TYUGY3","short_pith_number":"pith:ZOKIQFHC","schema_version":"1.0","canonical_sha256":"cb948814e20b04085498ff97e9e286c6e4cc87b7b679ccb4596f7b08a9a2acea","source":{"kind":"arxiv","id":"1605.09346","version":1},"attestation_state":"computed","paper":{"title":"Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anton Osokin, Isabella Lukasewitz, Jean-Baptiste Alayrac, Puneet K. Dokania, Simon Lacoste-Julien","submitted_at":"2016-05-30T18:15:30Z","abstract_excerpt":"In this paper, we propose several improvements on the block-coordinate Frank-Wolfe (BCFW) algorithm from Lacoste-Julien et al. (2013) recently used to optimize the structured support vector machine (SSVM) objective in the context of structured prediction, though it has wider applications. The key intuition behind our improvements is that the estimates of block gaps maintained by BCFW reveal the block suboptimality that can be used as an adaptive criterion. First, we sample objects at each iteration of BCFW in an adaptive non-uniform way via gapbased sampling. Second, we incorporate pairwise an"},"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":"1605.09346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-30T18:15:30Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"6ccb4bc93833534859b909b475aa79b9daf4d628c2185bdb932d0052b8bb459a","abstract_canon_sha256":"951e033ce0b2cef2c816484a68dffd0e5db44215406190f568ad71bd831547d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:10.774614Z","signature_b64":"zBI/O9jXRocAYIfuM8dp850hVLeSO/fW2TwxE066pX+hhc963GvlLLtiSAtfOqtyMesq0qoJKsJym2LPp2lIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb948814e20b04085498ff97e9e286c6e4cc87b7b679ccb4596f7b08a9a2acea","last_reissued_at":"2026-05-18T01:13:10.774199Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:10.774199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anton Osokin, Isabella Lukasewitz, Jean-Baptiste Alayrac, Puneet K. Dokania, Simon Lacoste-Julien","submitted_at":"2016-05-30T18:15:30Z","abstract_excerpt":"In this paper, we propose several improvements on the block-coordinate Frank-Wolfe (BCFW) algorithm from Lacoste-Julien et al. (2013) recently used to optimize the structured support vector machine (SSVM) objective in the context of structured prediction, though it has wider applications. The key intuition behind our improvements is that the estimates of block gaps maintained by BCFW reveal the block suboptimality that can be used as an adaptive criterion. First, we sample objects at each iteration of BCFW in an adaptive non-uniform way via gapbased sampling. Second, we incorporate pairwise an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.09346","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":"1605.09346","created_at":"2026-05-18T01:13:10.774270+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.09346v1","created_at":"2026-05-18T01:13:10.774270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.09346","created_at":"2026-05-18T01:13:10.774270+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOKIQFHCBMCA","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOKIQFHCBMCAQVEY","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOKIQFHC","created_at":"2026-05-18T12:30:55.937587+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/ZOKIQFHCBMCAQVEY76L6TYUGY3","json":"https://pith.science/pith/ZOKIQFHCBMCAQVEY76L6TYUGY3.json","graph_json":"https://pith.science/api/pith-number/ZOKIQFHCBMCAQVEY76L6TYUGY3/graph.json","events_json":"https://pith.science/api/pith-number/ZOKIQFHCBMCAQVEY76L6TYUGY3/events.json","paper":"https://pith.science/paper/ZOKIQFHC"},"agent_actions":{"view_html":"https://pith.science/pith/ZOKIQFHCBMCAQVEY76L6TYUGY3","download_json":"https://pith.science/pith/ZOKIQFHCBMCAQVEY76L6TYUGY3.json","view_paper":"https://pith.science/paper/ZOKIQFHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.09346&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOKIQFHCBMCAQVEY76L6TYUGY3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOKIQFHCBMCAQVEY76L6TYUGY3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOKIQFHCBMCAQVEY76L6TYUGY3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOKIQFHCBMCAQVEY76L6TYUGY3/action/storage_attestation","attest_author":"https://pith.science/pith/ZOKIQFHCBMCAQVEY76L6TYUGY3/action/author_attestation","sign_citation":"https://pith.science/pith/ZOKIQFHCBMCAQVEY76L6TYUGY3/action/citation_signature","submit_replication":"https://pith.science/pith/ZOKIQFHCBMCAQVEY76L6TYUGY3/action/replication_record"}},"created_at":"2026-05-18T01:13:10.774270+00:00","updated_at":"2026-05-18T01:13:10.774270+00:00"}