{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FTSW45DHQE7KNNMLXF3WUOK65M","short_pith_number":"pith:FTSW45DH","schema_version":"1.0","canonical_sha256":"2ce56e7467813ea6b58bb9776a395eeb32dbae5d193901780915ef6ddbe2a937","source":{"kind":"arxiv","id":"1810.05188","version":2},"attestation_state":"computed","paper":{"title":"Fighting Contextual Bandits with Stochastic Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ambuj Tewari, Young Hun Jung","submitted_at":"2018-10-11T18:07:43Z","abstract_excerpt":"We introduce a new stochastic smoothing perspective to study adversarial contextual bandit problems. We propose a general algorithm template that represents random perturbation based algorithms and identify several perturbation distributions that lead to strong regret bounds. Using the idea of smoothness, we provide an $O(\\sqrt{T})$ zero-order bound for the vanilla algorithm and an $O(L^{*2/3}_{T})$ first-order bound for the clipped version. These bounds hold when the algorithms use with a variety of distributions that have a bounded hazard rate. Our algorithm template includes EXP4 as a speci"},"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":"1810.05188","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-11T18:07:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4c8951bc3a063b1c397cf834717813e883a5f74dcb7652e5b598b27e5e38950b","abstract_canon_sha256":"130371338e5d2fe47e888cc1ccc90894251bf868e667fe4cfdf0abd22c5b052e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:42.992973Z","signature_b64":"S5quk+nEB9AoPBihIbe/gDE91xqKaNlK8HnCyLcLiGJrrl9rgY+P6wAP/6ZD5aPmbpQ5LqjCDcTRZJmI5AYECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ce56e7467813ea6b58bb9776a395eeb32dbae5d193901780915ef6ddbe2a937","last_reissued_at":"2026-05-17T23:43:42.992426Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:42.992426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fighting Contextual Bandits with Stochastic Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ambuj Tewari, Young Hun Jung","submitted_at":"2018-10-11T18:07:43Z","abstract_excerpt":"We introduce a new stochastic smoothing perspective to study adversarial contextual bandit problems. We propose a general algorithm template that represents random perturbation based algorithms and identify several perturbation distributions that lead to strong regret bounds. Using the idea of smoothness, we provide an $O(\\sqrt{T})$ zero-order bound for the vanilla algorithm and an $O(L^{*2/3}_{T})$ first-order bound for the clipped version. These bounds hold when the algorithms use with a variety of distributions that have a bounded hazard rate. Our algorithm template includes EXP4 as a speci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05188","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":""},"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":"1810.05188","created_at":"2026-05-17T23:43:42.992513+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.05188v2","created_at":"2026-05-17T23:43:42.992513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05188","created_at":"2026-05-17T23:43:42.992513+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTSW45DHQE7K","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTSW45DHQE7KNNML","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTSW45DH","created_at":"2026-05-18T12:32:25.280505+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/FTSW45DHQE7KNNMLXF3WUOK65M","json":"https://pith.science/pith/FTSW45DHQE7KNNMLXF3WUOK65M.json","graph_json":"https://pith.science/api/pith-number/FTSW45DHQE7KNNMLXF3WUOK65M/graph.json","events_json":"https://pith.science/api/pith-number/FTSW45DHQE7KNNMLXF3WUOK65M/events.json","paper":"https://pith.science/paper/FTSW45DH"},"agent_actions":{"view_html":"https://pith.science/pith/FTSW45DHQE7KNNMLXF3WUOK65M","download_json":"https://pith.science/pith/FTSW45DHQE7KNNMLXF3WUOK65M.json","view_paper":"https://pith.science/paper/FTSW45DH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.05188&json=true","fetch_graph":"https://pith.science/api/pith-number/FTSW45DHQE7KNNMLXF3WUOK65M/graph.json","fetch_events":"https://pith.science/api/pith-number/FTSW45DHQE7KNNMLXF3WUOK65M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTSW45DHQE7KNNMLXF3WUOK65M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTSW45DHQE7KNNMLXF3WUOK65M/action/storage_attestation","attest_author":"https://pith.science/pith/FTSW45DHQE7KNNMLXF3WUOK65M/action/author_attestation","sign_citation":"https://pith.science/pith/FTSW45DHQE7KNNMLXF3WUOK65M/action/citation_signature","submit_replication":"https://pith.science/pith/FTSW45DHQE7KNNMLXF3WUOK65M/action/replication_record"}},"created_at":"2026-05-17T23:43:42.992513+00:00","updated_at":"2026-05-17T23:43:42.992513+00:00"}