{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AENRBDSNRMDG4T7ZOCQR6KAHVU","short_pith_number":"pith:AENRBDSN","schema_version":"1.0","canonical_sha256":"011b108e4d8b066e4ff970a11f2807ad043d46d9e850b19d8f392e495d38d86f","source":{"kind":"arxiv","id":"2410.02476","version":2},"attestation_state":"computed","paper":{"title":"Online Convex Optimization with a Separation Oracle","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Zakaria Mhammedi","submitted_at":"2024-10-03T13:35:08Z","abstract_excerpt":"In this paper, we introduce a new projection-free algorithm for Online Convex Optimization (OCO) with a state-of-the-art regret guarantee among separation-based algorithms. Existing projection-free methods based on the classical Frank-Wolfe algorithm achieve a suboptimal regret bound of $O(T^{3/4})$, while more recent separation-based approaches guarantee a regret bound of $O(\\kappa \\sqrt{T})$, where $\\kappa$ denotes the asphericity of the feasible set, defined as the ratio of the radii of the containing and contained balls. However, for ill-conditioned sets, $\\kappa$ can be arbitrarily large,"},"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":"2410.02476","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T13:35:08Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"6cdaa86a54563cd51fc5cdf14da06b0007c2fafcbe787321c21a43546f052ace","abstract_canon_sha256":"b4d978f1366ac76c3a8b2ab96435553fef60b94f757c4adafc068c1c30a2c654"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:53.413528Z","signature_b64":"mYVPG+SfPFa5by0zcKO2Xuy2os3L2mDpVjakcsGr/HlDMHr3aj2uBPqK4E6c8rWhBv3OOO3iFJ7CtNLK8eZMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"011b108e4d8b066e4ff970a11f2807ad043d46d9e850b19d8f392e495d38d86f","last_reissued_at":"2026-07-05T09:16:53.413055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:53.413055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Convex Optimization with a Separation Oracle","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Zakaria Mhammedi","submitted_at":"2024-10-03T13:35:08Z","abstract_excerpt":"In this paper, we introduce a new projection-free algorithm for Online Convex Optimization (OCO) with a state-of-the-art regret guarantee among separation-based algorithms. Existing projection-free methods based on the classical Frank-Wolfe algorithm achieve a suboptimal regret bound of $O(T^{3/4})$, while more recent separation-based approaches guarantee a regret bound of $O(\\kappa \\sqrt{T})$, where $\\kappa$ denotes the asphericity of the feasible set, defined as the ratio of the radii of the containing and contained balls. However, for ill-conditioned sets, $\\kappa$ can be arbitrarily large,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02476","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/2410.02476/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":"2410.02476","created_at":"2026-07-05T09:16:53.413111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02476v2","created_at":"2026-07-05T09:16:53.413111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02476","created_at":"2026-07-05T09:16:53.413111+00:00"},{"alias_kind":"pith_short_12","alias_value":"AENRBDSNRMDG","created_at":"2026-07-05T09:16:53.413111+00:00"},{"alias_kind":"pith_short_16","alias_value":"AENRBDSNRMDG4T7Z","created_at":"2026-07-05T09:16:53.413111+00:00"},{"alias_kind":"pith_short_8","alias_value":"AENRBDSN","created_at":"2026-07-05T09:16:53.413111+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11127","citing_title":"A Regularized Online Newton Method for Stochastic Convex Bandits with Linear Vanishing Noise","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AENRBDSNRMDG4T7ZOCQR6KAHVU","json":"https://pith.science/pith/AENRBDSNRMDG4T7ZOCQR6KAHVU.json","graph_json":"https://pith.science/api/pith-number/AENRBDSNRMDG4T7ZOCQR6KAHVU/graph.json","events_json":"https://pith.science/api/pith-number/AENRBDSNRMDG4T7ZOCQR6KAHVU/events.json","paper":"https://pith.science/paper/AENRBDSN"},"agent_actions":{"view_html":"https://pith.science/pith/AENRBDSNRMDG4T7ZOCQR6KAHVU","download_json":"https://pith.science/pith/AENRBDSNRMDG4T7ZOCQR6KAHVU.json","view_paper":"https://pith.science/paper/AENRBDSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02476&json=true","fetch_graph":"https://pith.science/api/pith-number/AENRBDSNRMDG4T7ZOCQR6KAHVU/graph.json","fetch_events":"https://pith.science/api/pith-number/AENRBDSNRMDG4T7ZOCQR6KAHVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AENRBDSNRMDG4T7ZOCQR6KAHVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AENRBDSNRMDG4T7ZOCQR6KAHVU/action/storage_attestation","attest_author":"https://pith.science/pith/AENRBDSNRMDG4T7ZOCQR6KAHVU/action/author_attestation","sign_citation":"https://pith.science/pith/AENRBDSNRMDG4T7ZOCQR6KAHVU/action/citation_signature","submit_replication":"https://pith.science/pith/AENRBDSNRMDG4T7ZOCQR6KAHVU/action/replication_record"}},"created_at":"2026-07-05T09:16:53.413111+00:00","updated_at":"2026-07-05T09:16:53.413111+00:00"}