{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NKNT5KEWW7ISKDBIKWF33M5ET2","short_pith_number":"pith:NKNT5KEW","schema_version":"1.0","canonical_sha256":"6a9b3ea896b7d1250c28558bbdb3a49e81cb8772a9a04512d3f333444e804ee7","source":{"kind":"arxiv","id":"2502.05019","version":1},"attestation_state":"computed","paper":{"title":"$O(\\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Abhishek Sinha, Rahul Vaze","submitted_at":"2025-02-07T15:47:04Z","abstract_excerpt":"The constrained version of the standard online convex optimization (OCO) framework, called COCO is considered, where on every round, a convex cost function and a convex constraint function are revealed to the learner after it chooses the action for that round. The objective is to simultaneously minimize the static regret and cumulative constraint violation (CCV). An algorithm is proposed that guarantees a static regret of $O(\\sqrt{T})$ and a CCV of $\\min\\{\\cV, O(\\sqrt{T}\\log T) \\}$, where $\\cV$ depends on the distance between the consecutively revealed constraint sets, the shape of constraint "},"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":"2502.05019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T15:47:04Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"d11d358f35fc64c21a770e7e81189b886442e76c34338c3e2436083bc4b94695","abstract_canon_sha256":"9484d1805cc8ebca86ef3d8e7ec25c2ee897d817a0c5efc373b6ba2bdb7ce19c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:33.688753Z","signature_b64":"dMxAQEbXghqrmBQ7e0VMYnsXf0+UpfSDFmUWM0BpzOpDPyT/gCyYZn2kR0cLxXNIe/cthkxVcGGpo6QFFfFfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a9b3ea896b7d1250c28558bbdb3a49e81cb8772a9a04512d3f333444e804ee7","last_reissued_at":"2026-07-05T10:11:33.688267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:33.688267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$O(\\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Abhishek Sinha, Rahul Vaze","submitted_at":"2025-02-07T15:47:04Z","abstract_excerpt":"The constrained version of the standard online convex optimization (OCO) framework, called COCO is considered, where on every round, a convex cost function and a convex constraint function are revealed to the learner after it chooses the action for that round. The objective is to simultaneously minimize the static regret and cumulative constraint violation (CCV). An algorithm is proposed that guarantees a static regret of $O(\\sqrt{T})$ and a CCV of $\\min\\{\\cV, O(\\sqrt{T}\\log T) \\}$, where $\\cV$ depends on the distance between the consecutively revealed constraint sets, the shape of constraint "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05019","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/2502.05019/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":"2502.05019","created_at":"2026-07-05T10:11:33.688326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05019v1","created_at":"2026-07-05T10:11:33.688326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05019","created_at":"2026-07-05T10:11:33.688326+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKNT5KEWW7IS","created_at":"2026-07-05T10:11:33.688326+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKNT5KEWW7ISKDBI","created_at":"2026-07-05T10:11:33.688326+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKNT5KEW","created_at":"2026-07-05T10:11:33.688326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08452","citing_title":"Theoretical Foundations of Continual Learning via Drift-Plus-Penalty","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21107","citing_title":"A Geometric Approach to Constrained Online Learning","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NKNT5KEWW7ISKDBIKWF33M5ET2","json":"https://pith.science/pith/NKNT5KEWW7ISKDBIKWF33M5ET2.json","graph_json":"https://pith.science/api/pith-number/NKNT5KEWW7ISKDBIKWF33M5ET2/graph.json","events_json":"https://pith.science/api/pith-number/NKNT5KEWW7ISKDBIKWF33M5ET2/events.json","paper":"https://pith.science/paper/NKNT5KEW"},"agent_actions":{"view_html":"https://pith.science/pith/NKNT5KEWW7ISKDBIKWF33M5ET2","download_json":"https://pith.science/pith/NKNT5KEWW7ISKDBIKWF33M5ET2.json","view_paper":"https://pith.science/paper/NKNT5KEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05019&json=true","fetch_graph":"https://pith.science/api/pith-number/NKNT5KEWW7ISKDBIKWF33M5ET2/graph.json","fetch_events":"https://pith.science/api/pith-number/NKNT5KEWW7ISKDBIKWF33M5ET2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKNT5KEWW7ISKDBIKWF33M5ET2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKNT5KEWW7ISKDBIKWF33M5ET2/action/storage_attestation","attest_author":"https://pith.science/pith/NKNT5KEWW7ISKDBIKWF33M5ET2/action/author_attestation","sign_citation":"https://pith.science/pith/NKNT5KEWW7ISKDBIKWF33M5ET2/action/citation_signature","submit_replication":"https://pith.science/pith/NKNT5KEWW7ISKDBIKWF33M5ET2/action/replication_record"}},"created_at":"2026-07-05T10:11:33.688326+00:00","updated_at":"2026-07-05T10:11:33.688326+00:00"}