{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CR3AK2P6D2FBKEU4UWG2HTYABV","short_pith_number":"pith:CR3AK2P6","schema_version":"1.0","canonical_sha256":"14760569fe1e8a15129ca58da3cf000d73c0140155e4b5ac157244fdc6444f66","source":{"kind":"arxiv","id":"2412.08060","version":2},"attestation_state":"computed","paper":{"title":"An Optimistic Algorithm for Online Convex Optimization with Adversarial Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Jordan Lekeufack, Michael I. Jordan","submitted_at":"2024-12-11T03:06:42Z","abstract_excerpt":"We study Online Convex Optimization (OCO) with adversarial constraints, where an online algorithm must make sequential decisions to minimize both convex loss functions and cumulative constraint violations. We focus on a setting where the algorithm has access to predictions of the loss and constraint functions. Our results show that we can improve the current best bounds of $ O(\\sqrt{T}) $ regret and $ \\tilde{O}(\\sqrt{T}) $ cumulative constraint violations to $ O(\\sqrt{E_T(f)}) $ and $ \\tilde{O}(\\sqrt{E_T(g^+)}) $, respectively, where $ E_T(f) $ and $E_T(g^+)$ represent the cumulative predictio"},"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":"2412.08060","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-12-11T03:06:42Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"37e65e5c5ec044d6c75d66a5c8d66f0c0a93fb40bc89642a6c7f4e88ad2517e3","abstract_canon_sha256":"b98fd3ec16d0da004500ed9cdd32a9ec3d638d803d8e6d5e2a28b74c12ee927f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:03.348513Z","signature_b64":"JMD/NU1+4e1BMCECNypzWBi0yTJBNbKL7kfzh4eFdno29YJG2uIW8W4s8aOs8SAWbksgVJzbjo4bSUx8fjLNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14760569fe1e8a15129ca58da3cf000d73c0140155e4b5ac157244fdc6444f66","last_reissued_at":"2026-07-05T10:30:03.348043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:03.348043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Optimistic Algorithm for Online Convex Optimization with Adversarial Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Jordan Lekeufack, Michael I. Jordan","submitted_at":"2024-12-11T03:06:42Z","abstract_excerpt":"We study Online Convex Optimization (OCO) with adversarial constraints, where an online algorithm must make sequential decisions to minimize both convex loss functions and cumulative constraint violations. We focus on a setting where the algorithm has access to predictions of the loss and constraint functions. Our results show that we can improve the current best bounds of $ O(\\sqrt{T}) $ regret and $ \\tilde{O}(\\sqrt{T}) $ cumulative constraint violations to $ O(\\sqrt{E_T(f)}) $ and $ \\tilde{O}(\\sqrt{E_T(g^+)}) $, respectively, where $ E_T(f) $ and $E_T(g^+)$ represent the cumulative predictio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08060","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/2412.08060/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":"2412.08060","created_at":"2026-07-05T10:30:03.348094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08060v2","created_at":"2026-07-05T10:30:03.348094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08060","created_at":"2026-07-05T10:30:03.348094+00:00"},{"alias_kind":"pith_short_12","alias_value":"CR3AK2P6D2FB","created_at":"2026-07-05T10:30:03.348094+00:00"},{"alias_kind":"pith_short_16","alias_value":"CR3AK2P6D2FBKEU4","created_at":"2026-07-05T10:30:03.348094+00:00"},{"alias_kind":"pith_short_8","alias_value":"CR3AK2P6","created_at":"2026-07-05T10:30:03.348094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03831","citing_title":"Online Learning with Gradient-Variation Interval Regret","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31480","citing_title":"Constrained Online Convex Optimization without Slater's Condition","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CR3AK2P6D2FBKEU4UWG2HTYABV","json":"https://pith.science/pith/CR3AK2P6D2FBKEU4UWG2HTYABV.json","graph_json":"https://pith.science/api/pith-number/CR3AK2P6D2FBKEU4UWG2HTYABV/graph.json","events_json":"https://pith.science/api/pith-number/CR3AK2P6D2FBKEU4UWG2HTYABV/events.json","paper":"https://pith.science/paper/CR3AK2P6"},"agent_actions":{"view_html":"https://pith.science/pith/CR3AK2P6D2FBKEU4UWG2HTYABV","download_json":"https://pith.science/pith/CR3AK2P6D2FBKEU4UWG2HTYABV.json","view_paper":"https://pith.science/paper/CR3AK2P6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08060&json=true","fetch_graph":"https://pith.science/api/pith-number/CR3AK2P6D2FBKEU4UWG2HTYABV/graph.json","fetch_events":"https://pith.science/api/pith-number/CR3AK2P6D2FBKEU4UWG2HTYABV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CR3AK2P6D2FBKEU4UWG2HTYABV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CR3AK2P6D2FBKEU4UWG2HTYABV/action/storage_attestation","attest_author":"https://pith.science/pith/CR3AK2P6D2FBKEU4UWG2HTYABV/action/author_attestation","sign_citation":"https://pith.science/pith/CR3AK2P6D2FBKEU4UWG2HTYABV/action/citation_signature","submit_replication":"https://pith.science/pith/CR3AK2P6D2FBKEU4UWG2HTYABV/action/replication_record"}},"created_at":"2026-07-05T10:30:03.348094+00:00","updated_at":"2026-07-05T10:30:03.348094+00:00"}