{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:FHHTKX2EMR62VEVJPZ5RCT2AO6","short_pith_number":"pith:FHHTKX2E","schema_version":"1.0","canonical_sha256":"29cf355f44647daa92a97e7b114f40778c4b3827fbf9f609f098ca9877bb72c0","source":{"kind":"arxiv","id":"1106.2369","version":1},"attestation_state":"computed","paper":{"title":"Efficient Optimal Learning for Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Hsu, John Langford, Lev Reyzin, Miroslav Dudik, Nikos Karampatziakis, Satyen Kale, Tong Zhang","submitted_at":"2011-06-13T01:57:52Z","abstract_excerpt":"We address the problem of learning in an online setting where the learner repeatedly observes features, selects among a set of actions, and receives reward for the action taken. We provide the first efficient algorithm with an optimal regret. Our algorithm uses a cost sensitive classification learner as an oracle and has a running time $\\mathrm{polylog}(N)$, where $N$ is the number of classification rules among which the oracle might choose. This is exponentially faster than all previous algorithms that achieve optimal regret in this setting. Our formulation also enables us to create an algori"},"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":"1106.2369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-13T01:57:52Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a1103efa859ed1df26652cfe1e7c42ef3b06b8fb7942d91686952f475f2713c1","abstract_canon_sha256":"9a95be48c780e195f942e2d2725746cbf60516f3404867c8a598ce75e35f9f4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:19:54.351466Z","signature_b64":"MQkSnRJFRUpbsaZ+dncrPc2zTM4zprPA9WwIgvlxZ6srAz3W2LdnC1UBvg4Wcge3hl86wZJsSagbPscnFgwNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29cf355f44647daa92a97e7b114f40778c4b3827fbf9f609f098ca9877bb72c0","last_reissued_at":"2026-05-18T04:19:54.350710Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:19:54.350710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Optimal Learning for Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Hsu, John Langford, Lev Reyzin, Miroslav Dudik, Nikos Karampatziakis, Satyen Kale, Tong Zhang","submitted_at":"2011-06-13T01:57:52Z","abstract_excerpt":"We address the problem of learning in an online setting where the learner repeatedly observes features, selects among a set of actions, and receives reward for the action taken. We provide the first efficient algorithm with an optimal regret. Our algorithm uses a cost sensitive classification learner as an oracle and has a running time $\\mathrm{polylog}(N)$, where $N$ is the number of classification rules among which the oracle might choose. This is exponentially faster than all previous algorithms that achieve optimal regret in this setting. Our formulation also enables us to create an algori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.2369","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":""},"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":"1106.2369","created_at":"2026-05-18T04:19:54.350832+00:00"},{"alias_kind":"arxiv_version","alias_value":"1106.2369v1","created_at":"2026-05-18T04:19:54.350832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.2369","created_at":"2026-05-18T04:19:54.350832+00:00"},{"alias_kind":"pith_short_12","alias_value":"FHHTKX2EMR62","created_at":"2026-05-18T12:26:28.662955+00:00"},{"alias_kind":"pith_short_16","alias_value":"FHHTKX2EMR62VEVJ","created_at":"2026-05-18T12:26:28.662955+00:00"},{"alias_kind":"pith_short_8","alias_value":"FHHTKX2E","created_at":"2026-05-18T12:26:28.662955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.23351","citing_title":"Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2502.16156","citing_title":"A Review of Causal Decision Making","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12316","citing_title":"Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06190","citing_title":"Constrained Contextual Bandits with Adversarial Contexts","ref_index":291,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07155","citing_title":"Regret-Oracle Complexity Tradeoffs in Agnostic Online Learning","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FHHTKX2EMR62VEVJPZ5RCT2AO6","json":"https://pith.science/pith/FHHTKX2EMR62VEVJPZ5RCT2AO6.json","graph_json":"https://pith.science/api/pith-number/FHHTKX2EMR62VEVJPZ5RCT2AO6/graph.json","events_json":"https://pith.science/api/pith-number/FHHTKX2EMR62VEVJPZ5RCT2AO6/events.json","paper":"https://pith.science/paper/FHHTKX2E"},"agent_actions":{"view_html":"https://pith.science/pith/FHHTKX2EMR62VEVJPZ5RCT2AO6","download_json":"https://pith.science/pith/FHHTKX2EMR62VEVJPZ5RCT2AO6.json","view_paper":"https://pith.science/paper/FHHTKX2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1106.2369&json=true","fetch_graph":"https://pith.science/api/pith-number/FHHTKX2EMR62VEVJPZ5RCT2AO6/graph.json","fetch_events":"https://pith.science/api/pith-number/FHHTKX2EMR62VEVJPZ5RCT2AO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FHHTKX2EMR62VEVJPZ5RCT2AO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FHHTKX2EMR62VEVJPZ5RCT2AO6/action/storage_attestation","attest_author":"https://pith.science/pith/FHHTKX2EMR62VEVJPZ5RCT2AO6/action/author_attestation","sign_citation":"https://pith.science/pith/FHHTKX2EMR62VEVJPZ5RCT2AO6/action/citation_signature","submit_replication":"https://pith.science/pith/FHHTKX2EMR62VEVJPZ5RCT2AO6/action/replication_record"}},"created_at":"2026-05-18T04:19:54.350832+00:00","updated_at":"2026-05-18T04:19:54.350832+00:00"}