{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KF2TTPNXDB2YKQV723755CYNHN","short_pith_number":"pith:KF2TTPNX","schema_version":"1.0","canonical_sha256":"517539bdb718758542bfd6ffde8b0d3b76446e273a4c883426d587bd9ada5614","source":{"kind":"arxiv","id":"1905.01435","version":3},"attestation_state":"computed","paper":{"title":"Tight Regret Bounds for Infinite-armed Linear Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Xi Chen, Yingkai Li, Yining Wang, Yuan Zhou","submitted_at":"2019-05-04T05:51:30Z","abstract_excerpt":"Linear contextual bandit is an important class of sequential decision making problems with a wide range of applications to recommender systems, online advertising, healthcare, and many other machine learning related tasks. While there is a lot of prior research, tight regret bounds of linear contextual bandit with infinite action sets remain open. In this paper, we address this open problem by considering the linear contextual bandit with (changing) infinite action sets. We prove a regret upper bound on the order of $O(\\sqrt{d^2T\\log T})\\times \\text{poly}(\\log\\log T)$ where $d$ is the domain d"},"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":"1905.01435","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-04T05:51:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8c3ceb61c6b4ad05cd49837d3270f5436537fc2760436121b7701858aa242cf0","abstract_canon_sha256":"3cb89b8ead6337829ba03074d9955b509fdf1d6b0a90d827dcc15a56b32396cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:05.095572Z","signature_b64":"crmP5PFeJUZOuYNT2ImRdM7R9QDYd6BBTS1Bl3pHnymg2tQ4Pr/8RdTu6hPXKhLiB/AR1tRZ5gKeqWkF3knaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"517539bdb718758542bfd6ffde8b0d3b76446e273a4c883426d587bd9ada5614","last_reissued_at":"2026-07-05T02:10:05.095147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:05.095147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tight Regret Bounds for Infinite-armed Linear Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Xi Chen, Yingkai Li, Yining Wang, Yuan Zhou","submitted_at":"2019-05-04T05:51:30Z","abstract_excerpt":"Linear contextual bandit is an important class of sequential decision making problems with a wide range of applications to recommender systems, online advertising, healthcare, and many other machine learning related tasks. While there is a lot of prior research, tight regret bounds of linear contextual bandit with infinite action sets remain open. In this paper, we address this open problem by considering the linear contextual bandit with (changing) infinite action sets. We prove a regret upper bound on the order of $O(\\sqrt{d^2T\\log T})\\times \\text{poly}(\\log\\log T)$ where $d$ is the domain d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01435","kind":"arxiv","version":3},"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/1905.01435/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":"1905.01435","created_at":"2026-07-05T02:10:05.095208+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.01435v3","created_at":"2026-07-05T02:10:05.095208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01435","created_at":"2026-07-05T02:10:05.095208+00:00"},{"alias_kind":"pith_short_12","alias_value":"KF2TTPNXDB2Y","created_at":"2026-07-05T02:10:05.095208+00:00"},{"alias_kind":"pith_short_16","alias_value":"KF2TTPNXDB2YKQV7","created_at":"2026-07-05T02:10:05.095208+00:00"},{"alias_kind":"pith_short_8","alias_value":"KF2TTPNX","created_at":"2026-07-05T02:10:05.095208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.02109","citing_title":"Stochastic Linear Optimization with Adversarial Corruption","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KF2TTPNXDB2YKQV723755CYNHN","json":"https://pith.science/pith/KF2TTPNXDB2YKQV723755CYNHN.json","graph_json":"https://pith.science/api/pith-number/KF2TTPNXDB2YKQV723755CYNHN/graph.json","events_json":"https://pith.science/api/pith-number/KF2TTPNXDB2YKQV723755CYNHN/events.json","paper":"https://pith.science/paper/KF2TTPNX"},"agent_actions":{"view_html":"https://pith.science/pith/KF2TTPNXDB2YKQV723755CYNHN","download_json":"https://pith.science/pith/KF2TTPNXDB2YKQV723755CYNHN.json","view_paper":"https://pith.science/paper/KF2TTPNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.01435&json=true","fetch_graph":"https://pith.science/api/pith-number/KF2TTPNXDB2YKQV723755CYNHN/graph.json","fetch_events":"https://pith.science/api/pith-number/KF2TTPNXDB2YKQV723755CYNHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KF2TTPNXDB2YKQV723755CYNHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KF2TTPNXDB2YKQV723755CYNHN/action/storage_attestation","attest_author":"https://pith.science/pith/KF2TTPNXDB2YKQV723755CYNHN/action/author_attestation","sign_citation":"https://pith.science/pith/KF2TTPNXDB2YKQV723755CYNHN/action/citation_signature","submit_replication":"https://pith.science/pith/KF2TTPNXDB2YKQV723755CYNHN/action/replication_record"}},"created_at":"2026-07-05T02:10:05.095208+00:00","updated_at":"2026-07-05T02:10:05.095208+00:00"}