{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GROEIPBL3DNS2RAZIHKKN3SMHG","short_pith_number":"pith:GROEIPBL","schema_version":"1.0","canonical_sha256":"345c443c2bd8db2d441941d4a6ee4c39b649fec2733a1e1640d50bbec7323076","source":{"kind":"arxiv","id":"2205.11470","version":1},"attestation_state":"computed","paper":{"title":"Exploiting the Curvature of Feasible Sets for Faster Projection-Free Online Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Zakaria Mhammedi","submitted_at":"2022-05-23T17:13:46Z","abstract_excerpt":"In this paper, we develop new efficient projection-free algorithms for Online Convex Optimization (OCO). Online Gradient Descent (OGD) is an example of a classical OCO algorithm that guarantees the optimal $O(\\sqrt{T})$ regret bound. However, OGD and other projection-based OCO algorithms need to perform a Euclidean projection onto the feasible set $\\mathcal{C}\\subset \\mathbb{R}^d$ whenever their iterates step outside $\\mathcal{C}$. For various sets of interests, this projection step can be computationally costly, especially when the ambient dimension is large. This has motivated the developmen"},"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":"2205.11470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T17:13:46Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"8eff871ac05cac292cd034e99588745871fe800a7d52f88bd90e2abcde0a6d26","abstract_canon_sha256":"189738e8211e202675860ef0093b4090e7bb2917dacde040dc96c1d762b6cea6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:37.599819Z","signature_b64":"KW/yJtF+r1TBtd0cTVAuijsycyE5iEdntT96PCyN7DFCUWcbmOkZwL89U04GqIhwWGUvLZwRvPU5do/A5PFtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"345c443c2bd8db2d441941d4a6ee4c39b649fec2733a1e1640d50bbec7323076","last_reissued_at":"2026-07-05T04:25:37.599404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:37.599404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting the Curvature of Feasible Sets for Faster Projection-Free Online Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Zakaria Mhammedi","submitted_at":"2022-05-23T17:13:46Z","abstract_excerpt":"In this paper, we develop new efficient projection-free algorithms for Online Convex Optimization (OCO). Online Gradient Descent (OGD) is an example of a classical OCO algorithm that guarantees the optimal $O(\\sqrt{T})$ regret bound. However, OGD and other projection-based OCO algorithms need to perform a Euclidean projection onto the feasible set $\\mathcal{C}\\subset \\mathbb{R}^d$ whenever their iterates step outside $\\mathcal{C}$. For various sets of interests, this projection step can be computationally costly, especially when the ambient dimension is large. This has motivated the developmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11470","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.11470/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":"2205.11470","created_at":"2026-07-05T04:25:37.599456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11470v1","created_at":"2026-07-05T04:25:37.599456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11470","created_at":"2026-07-05T04:25:37.599456+00:00"},{"alias_kind":"pith_short_12","alias_value":"GROEIPBL3DNS","created_at":"2026-07-05T04:25:37.599456+00:00"},{"alias_kind":"pith_short_16","alias_value":"GROEIPBL3DNS2RAZ","created_at":"2026-07-05T04:25:37.599456+00:00"},{"alias_kind":"pith_short_8","alias_value":"GROEIPBL","created_at":"2026-07-05T04:25:37.599456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01685","citing_title":"Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GROEIPBL3DNS2RAZIHKKN3SMHG","json":"https://pith.science/pith/GROEIPBL3DNS2RAZIHKKN3SMHG.json","graph_json":"https://pith.science/api/pith-number/GROEIPBL3DNS2RAZIHKKN3SMHG/graph.json","events_json":"https://pith.science/api/pith-number/GROEIPBL3DNS2RAZIHKKN3SMHG/events.json","paper":"https://pith.science/paper/GROEIPBL"},"agent_actions":{"view_html":"https://pith.science/pith/GROEIPBL3DNS2RAZIHKKN3SMHG","download_json":"https://pith.science/pith/GROEIPBL3DNS2RAZIHKKN3SMHG.json","view_paper":"https://pith.science/paper/GROEIPBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11470&json=true","fetch_graph":"https://pith.science/api/pith-number/GROEIPBL3DNS2RAZIHKKN3SMHG/graph.json","fetch_events":"https://pith.science/api/pith-number/GROEIPBL3DNS2RAZIHKKN3SMHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GROEIPBL3DNS2RAZIHKKN3SMHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GROEIPBL3DNS2RAZIHKKN3SMHG/action/storage_attestation","attest_author":"https://pith.science/pith/GROEIPBL3DNS2RAZIHKKN3SMHG/action/author_attestation","sign_citation":"https://pith.science/pith/GROEIPBL3DNS2RAZIHKKN3SMHG/action/citation_signature","submit_replication":"https://pith.science/pith/GROEIPBL3DNS2RAZIHKKN3SMHG/action/replication_record"}},"created_at":"2026-07-05T04:25:37.599456+00:00","updated_at":"2026-07-05T04:25:37.599456+00:00"}