{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MGXMIYA32TBC633HYGWVDJM7MW","short_pith_number":"pith:MGXMIYA3","schema_version":"1.0","canonical_sha256":"61aec4601bd4c22f6f67c1ad51a59f65a9730515131da98bf720736a01a4cba7","source":{"kind":"arxiv","id":"2501.07201","version":2},"attestation_state":"computed","paper":{"title":"An Enhanced Zeroth-Order Stochastic Frank-Wolfe Framework for Constrained Finite-Sum Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Haishan Ye, Hao Di, Xiangyu Chang, Yinghui Huang","submitted_at":"2025-01-13T10:53:19Z","abstract_excerpt":"We propose an enhanced zeroth-order stochastic Frank-Wolfe framework to address constrained finite-sum optimization problems, a structure prevalent in large-scale machine-learning applications. Our method introduces a novel double variance reduction framework that effectively reduces the gradient approximation variance induced by zeroth-order oracles and the stochastic sampling variance from finite-sum objectives. By leveraging this framework, our algorithm achieves significant improvements in query efficiency, making it particularly well-suited for high-dimensional optimization tasks. Specifi"},"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":"2501.07201","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-13T10:53:19Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"5dd5e5f000d728ab1b919b6e8c9c2af4cccbd52231e5b203ab3f09b29fc8c366","abstract_canon_sha256":"0ec4dbf454cacf3fb9cb17602ad359f554e3d3ee71f3955823909896a04e38df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:22.031900Z","signature_b64":"r7ySzrMc3MnCCGtKQrenYPFQmXNgczy7SyGle4K63gCAajYTbKd8dtki9E3a3Mb5LqK8HNI4c5GcGCL38UznDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61aec4601bd4c22f6f67c1ad51a59f65a9730515131da98bf720736a01a4cba7","last_reissued_at":"2026-07-05T10:04:22.031341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:22.031341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Enhanced Zeroth-Order Stochastic Frank-Wolfe Framework for Constrained Finite-Sum Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Haishan Ye, Hao Di, Xiangyu Chang, Yinghui Huang","submitted_at":"2025-01-13T10:53:19Z","abstract_excerpt":"We propose an enhanced zeroth-order stochastic Frank-Wolfe framework to address constrained finite-sum optimization problems, a structure prevalent in large-scale machine-learning applications. Our method introduces a novel double variance reduction framework that effectively reduces the gradient approximation variance induced by zeroth-order oracles and the stochastic sampling variance from finite-sum objectives. By leveraging this framework, our algorithm achieves significant improvements in query efficiency, making it particularly well-suited for high-dimensional optimization tasks. Specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07201","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/2501.07201/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":"2501.07201","created_at":"2026-07-05T10:04:22.031402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07201v2","created_at":"2026-07-05T10:04:22.031402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07201","created_at":"2026-07-05T10:04:22.031402+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGXMIYA32TBC","created_at":"2026-07-05T10:04:22.031402+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGXMIYA32TBC633H","created_at":"2026-07-05T10:04:22.031402+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGXMIYA3","created_at":"2026-07-05T10:04:22.031402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20546","citing_title":"A Zeroth-Order Extra-Gradient Method for Black-Box Constrained Optimization","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGXMIYA32TBC633HYGWVDJM7MW","json":"https://pith.science/pith/MGXMIYA32TBC633HYGWVDJM7MW.json","graph_json":"https://pith.science/api/pith-number/MGXMIYA32TBC633HYGWVDJM7MW/graph.json","events_json":"https://pith.science/api/pith-number/MGXMIYA32TBC633HYGWVDJM7MW/events.json","paper":"https://pith.science/paper/MGXMIYA3"},"agent_actions":{"view_html":"https://pith.science/pith/MGXMIYA32TBC633HYGWVDJM7MW","download_json":"https://pith.science/pith/MGXMIYA32TBC633HYGWVDJM7MW.json","view_paper":"https://pith.science/paper/MGXMIYA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07201&json=true","fetch_graph":"https://pith.science/api/pith-number/MGXMIYA32TBC633HYGWVDJM7MW/graph.json","fetch_events":"https://pith.science/api/pith-number/MGXMIYA32TBC633HYGWVDJM7MW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGXMIYA32TBC633HYGWVDJM7MW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGXMIYA32TBC633HYGWVDJM7MW/action/storage_attestation","attest_author":"https://pith.science/pith/MGXMIYA32TBC633HYGWVDJM7MW/action/author_attestation","sign_citation":"https://pith.science/pith/MGXMIYA32TBC633HYGWVDJM7MW/action/citation_signature","submit_replication":"https://pith.science/pith/MGXMIYA32TBC633HYGWVDJM7MW/action/replication_record"}},"created_at":"2026-07-05T10:04:22.031402+00:00","updated_at":"2026-07-05T10:04:22.031402+00:00"}