{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:BKDYTHAO4ORIAXH7IJKD26GVGW","short_pith_number":"pith:BKDYTHAO","schema_version":"1.0","canonical_sha256":"0a87899c0ee3a2805cff42543d78d5358b4aa8a87d24e2a5baaf7eb8989e007c","source":{"kind":"arxiv","id":"1102.2490","version":5},"attestation_state":"computed","paper":{"title":"The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","math.OC","stat.TH"],"primary_cat":"math.ST","authors_text":"Aur\\'elien Garivier, Olivier Capp\\'e","submitted_at":"2011-02-12T10:03:21Z","abstract_excerpt":"This paper presents a finite-time analysis of the KL-UCB algorithm, an online, horizon-free index policy for stochastic bandit problems. We prove two distinct results: first, for arbitrary bounded rewards, the KL-UCB algorithm satisfies a uniformly better regret bound than UCB or UCB2; second, in the special case of Bernoulli rewards, it reaches the lower bound of Lai and Robbins. Furthermore, we show that simple adaptations of the KL-UCB algorithm are also optimal for specific classes of (possibly unbounded) rewards, including those generated from exponential families of distributions. A larg"},"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":"1102.2490","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2011-02-12T10:03:21Z","cross_cats_sorted":["cs.LG","cs.SY","math.OC","stat.TH"],"title_canon_sha256":"809cfa211461f01705559159b68f697b6e56578e350edf217527d7f1c6739664","abstract_canon_sha256":"4696ab5ef839beed3be386aca836fa80164a04dadd921e9333f4723281c948f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:14:41.233065Z","signature_b64":"zBzgnCKmvh2+sZDbCerYEwsJbCiBn1CCTZDj8mrMN3NRVLYYsh4kWvV7BbU3oknzSSIEyTCnJKOP3qgF40VfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a87899c0ee3a2805cff42543d78d5358b4aa8a87d24e2a5baaf7eb8989e007c","last_reissued_at":"2026-05-18T03:14:41.232336Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:14:41.232336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","math.OC","stat.TH"],"primary_cat":"math.ST","authors_text":"Aur\\'elien Garivier, Olivier Capp\\'e","submitted_at":"2011-02-12T10:03:21Z","abstract_excerpt":"This paper presents a finite-time analysis of the KL-UCB algorithm, an online, horizon-free index policy for stochastic bandit problems. We prove two distinct results: first, for arbitrary bounded rewards, the KL-UCB algorithm satisfies a uniformly better regret bound than UCB or UCB2; second, in the special case of Bernoulli rewards, it reaches the lower bound of Lai and Robbins. Furthermore, we show that simple adaptations of the KL-UCB algorithm are also optimal for specific classes of (possibly unbounded) rewards, including those generated from exponential families of distributions. A larg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1102.2490","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1102.2490","created_at":"2026-05-18T03:14:41.232454+00:00"},{"alias_kind":"arxiv_version","alias_value":"1102.2490v5","created_at":"2026-05-18T03:14:41.232454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1102.2490","created_at":"2026-05-18T03:14:41.232454+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKDYTHAO4ORI","created_at":"2026-05-18T12:26:24.575870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKDYTHAO4ORIAXH7","created_at":"2026-05-18T12:26:24.575870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKDYTHAO","created_at":"2026-05-18T12:26:24.575870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2604.19672","citing_title":"Budgeted Online Influence Maximization","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13738","citing_title":"Covariance-adapting algorithm for semi-bandits with application to sparse rewards","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKDYTHAO4ORIAXH7IJKD26GVGW","json":"https://pith.science/pith/BKDYTHAO4ORIAXH7IJKD26GVGW.json","graph_json":"https://pith.science/api/pith-number/BKDYTHAO4ORIAXH7IJKD26GVGW/graph.json","events_json":"https://pith.science/api/pith-number/BKDYTHAO4ORIAXH7IJKD26GVGW/events.json","paper":"https://pith.science/paper/BKDYTHAO"},"agent_actions":{"view_html":"https://pith.science/pith/BKDYTHAO4ORIAXH7IJKD26GVGW","download_json":"https://pith.science/pith/BKDYTHAO4ORIAXH7IJKD26GVGW.json","view_paper":"https://pith.science/paper/BKDYTHAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1102.2490&json=true","fetch_graph":"https://pith.science/api/pith-number/BKDYTHAO4ORIAXH7IJKD26GVGW/graph.json","fetch_events":"https://pith.science/api/pith-number/BKDYTHAO4ORIAXH7IJKD26GVGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKDYTHAO4ORIAXH7IJKD26GVGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKDYTHAO4ORIAXH7IJKD26GVGW/action/storage_attestation","attest_author":"https://pith.science/pith/BKDYTHAO4ORIAXH7IJKD26GVGW/action/author_attestation","sign_citation":"https://pith.science/pith/BKDYTHAO4ORIAXH7IJKD26GVGW/action/citation_signature","submit_replication":"https://pith.science/pith/BKDYTHAO4ORIAXH7IJKD26GVGW/action/replication_record"}},"created_at":"2026-05-18T03:14:41.232454+00:00","updated_at":"2026-05-18T03:14:41.232454+00:00"}