{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ILYXS65ER3TVELJ6GY3FGUT4K7","short_pith_number":"pith:ILYXS65E","schema_version":"1.0","canonical_sha256":"42f1797ba48ee7522d3e363653527c57df64c70b8ef2449eaeb055aaf3529074","source":{"kind":"arxiv","id":"1909.02553","version":4},"attestation_state":"computed","paper":{"title":"Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Nathan Kallus, Xiaojie Mao, Yichun Hu","submitted_at":"2019-09-05T17:51:14Z","abstract_excerpt":"We study a nonparametric contextual bandit problem where the expected reward functions belong to a H\\\"older class with smoothness parameter $\\beta$. We show how this interpolates between two extremes that were previously studied in isolation: non-differentiable bandits ($\\beta\\leq1$), where rate-optimal regret is achieved by running separate non-contextual bandits in different context regions, and parametric-response bandits (satisfying $\\beta=\\infty$), where rate-optimal regret can be achieved with minimal or no exploration due to infinite extrapolatability. We develop a novel algorithm that "},"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":"1909.02553","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-05T17:51:14Z","cross_cats_sorted":["cs.AI","cs.LG","math.OC","math.ST","stat.TH"],"title_canon_sha256":"b5b9810de5edee5e8c3e348070e4f0ac32bc95e92f85c5f4da9197ee25100f91","abstract_canon_sha256":"69ace3948011fe53c2ba5b18b6480be6c719847d6ba3350194b015fcca9a6163"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:41.534169Z","signature_b64":"CYBN23ePKxOqiEz378yuBcKcpXCVECOgp5ra9DW8whGKEMZbKmMg8veHrlkahP8+GFrtQXvzimyLOZHNrQRyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42f1797ba48ee7522d3e363653527c57df64c70b8ef2449eaeb055aaf3529074","last_reissued_at":"2026-07-05T01:34:41.533674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:41.533674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Nathan Kallus, Xiaojie Mao, Yichun Hu","submitted_at":"2019-09-05T17:51:14Z","abstract_excerpt":"We study a nonparametric contextual bandit problem where the expected reward functions belong to a H\\\"older class with smoothness parameter $\\beta$. We show how this interpolates between two extremes that were previously studied in isolation: non-differentiable bandits ($\\beta\\leq1$), where rate-optimal regret is achieved by running separate non-contextual bandits in different context regions, and parametric-response bandits (satisfying $\\beta=\\infty$), where rate-optimal regret can be achieved with minimal or no exploration due to infinite extrapolatability. We develop a novel algorithm that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02553","kind":"arxiv","version":4},"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/1909.02553/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":"1909.02553","created_at":"2026-07-05T01:34:41.533731+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.02553v4","created_at":"2026-07-05T01:34:41.533731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02553","created_at":"2026-07-05T01:34:41.533731+00:00"},{"alias_kind":"pith_short_12","alias_value":"ILYXS65ER3TV","created_at":"2026-07-05T01:34:41.533731+00:00"},{"alias_kind":"pith_short_16","alias_value":"ILYXS65ER3TVELJ6","created_at":"2026-07-05T01:34:41.533731+00:00"},{"alias_kind":"pith_short_8","alias_value":"ILYXS65E","created_at":"2026-07-05T01:34:41.533731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ILYXS65ER3TVELJ6GY3FGUT4K7","json":"https://pith.science/pith/ILYXS65ER3TVELJ6GY3FGUT4K7.json","graph_json":"https://pith.science/api/pith-number/ILYXS65ER3TVELJ6GY3FGUT4K7/graph.json","events_json":"https://pith.science/api/pith-number/ILYXS65ER3TVELJ6GY3FGUT4K7/events.json","paper":"https://pith.science/paper/ILYXS65E"},"agent_actions":{"view_html":"https://pith.science/pith/ILYXS65ER3TVELJ6GY3FGUT4K7","download_json":"https://pith.science/pith/ILYXS65ER3TVELJ6GY3FGUT4K7.json","view_paper":"https://pith.science/paper/ILYXS65E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.02553&json=true","fetch_graph":"https://pith.science/api/pith-number/ILYXS65ER3TVELJ6GY3FGUT4K7/graph.json","fetch_events":"https://pith.science/api/pith-number/ILYXS65ER3TVELJ6GY3FGUT4K7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ILYXS65ER3TVELJ6GY3FGUT4K7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ILYXS65ER3TVELJ6GY3FGUT4K7/action/storage_attestation","attest_author":"https://pith.science/pith/ILYXS65ER3TVELJ6GY3FGUT4K7/action/author_attestation","sign_citation":"https://pith.science/pith/ILYXS65ER3TVELJ6GY3FGUT4K7/action/citation_signature","submit_replication":"https://pith.science/pith/ILYXS65ER3TVELJ6GY3FGUT4K7/action/replication_record"}},"created_at":"2026-07-05T01:34:41.533731+00:00","updated_at":"2026-07-05T01:34:41.533731+00:00"}