{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:Q3CQZMBDTDOWCW7LUCWTVTPQ2W","short_pith_number":"pith:Q3CQZMBD","schema_version":"1.0","canonical_sha256":"86c50cb02398dd615beba0ad3acdf0d58945fd68fa4abb2510479f3f153a86f4","source":{"kind":"arxiv","id":"1512.04152","version":1},"attestation_state":"computed","paper":{"title":"Fighting Bandits with a New Kind of Smoothness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ambuj Tewari, Chansoo Lee, Jacob Abernethy","submitted_at":"2015-12-14T01:57:02Z","abstract_excerpt":"We define a novel family of algorithms for the adversarial multi-armed bandit problem, and provide a simple analysis technique based on convex smoothing. We prove two main results. First, we show that regularization via the \\emph{Tsallis entropy}, which includes EXP3 as a special case, achieves the $\\Theta(\\sqrt{TN})$ minimax regret. Second, we show that a wide class of perturbation methods achieve a near-optimal regret as low as $O(\\sqrt{TN \\log N})$ if the perturbation distribution has a bounded hazard rate. For example, the Gumbel, Weibull, Frechet, Pareto, and Gamma distributions all satis"},"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":"1512.04152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-14T01:57:02Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"1decc5038cd2a6d8ca5320847179fd7f3c55a48d5e7b4dca75e3b3c398a3aed5","abstract_canon_sha256":"ada3f0bf2ee0addfee202d9a6e38d9f2c3da270faa7d37d18ad43421114eddd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:22.974632Z","signature_b64":"nL55u1iYvG7cbVUm+iNZOiu34cVaN5CsmPRhBT0XP/+RpXaJ5XSZUFM5azXQ2lfKnoOalI16Q1d9BfOT+r8rCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86c50cb02398dd615beba0ad3acdf0d58945fd68fa4abb2510479f3f153a86f4","last_reissued_at":"2026-05-18T01:24:22.973900Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:22.973900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fighting Bandits with a New Kind of Smoothness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ambuj Tewari, Chansoo Lee, Jacob Abernethy","submitted_at":"2015-12-14T01:57:02Z","abstract_excerpt":"We define a novel family of algorithms for the adversarial multi-armed bandit problem, and provide a simple analysis technique based on convex smoothing. We prove two main results. First, we show that regularization via the \\emph{Tsallis entropy}, which includes EXP3 as a special case, achieves the $\\Theta(\\sqrt{TN})$ minimax regret. Second, we show that a wide class of perturbation methods achieve a near-optimal regret as low as $O(\\sqrt{TN \\log N})$ if the perturbation distribution has a bounded hazard rate. For example, the Gumbel, Weibull, Frechet, Pareto, and Gamma distributions all satis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.04152","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":"1512.04152","created_at":"2026-05-18T01:24:22.974022+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.04152v1","created_at":"2026-05-18T01:24:22.974022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.04152","created_at":"2026-05-18T01:24:22.974022+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3CQZMBDTDOW","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3CQZMBDTDOWCW7L","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3CQZMBD","created_at":"2026-05-18T12:29:37.295048+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/Q3CQZMBDTDOWCW7LUCWTVTPQ2W","json":"https://pith.science/pith/Q3CQZMBDTDOWCW7LUCWTVTPQ2W.json","graph_json":"https://pith.science/api/pith-number/Q3CQZMBDTDOWCW7LUCWTVTPQ2W/graph.json","events_json":"https://pith.science/api/pith-number/Q3CQZMBDTDOWCW7LUCWTVTPQ2W/events.json","paper":"https://pith.science/paper/Q3CQZMBD"},"agent_actions":{"view_html":"https://pith.science/pith/Q3CQZMBDTDOWCW7LUCWTVTPQ2W","download_json":"https://pith.science/pith/Q3CQZMBDTDOWCW7LUCWTVTPQ2W.json","view_paper":"https://pith.science/paper/Q3CQZMBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.04152&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3CQZMBDTDOWCW7LUCWTVTPQ2W/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3CQZMBDTDOWCW7LUCWTVTPQ2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3CQZMBDTDOWCW7LUCWTVTPQ2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3CQZMBDTDOWCW7LUCWTVTPQ2W/action/storage_attestation","attest_author":"https://pith.science/pith/Q3CQZMBDTDOWCW7LUCWTVTPQ2W/action/author_attestation","sign_citation":"https://pith.science/pith/Q3CQZMBDTDOWCW7LUCWTVTPQ2W/action/citation_signature","submit_replication":"https://pith.science/pith/Q3CQZMBDTDOWCW7LUCWTVTPQ2W/action/replication_record"}},"created_at":"2026-05-18T01:24:22.974022+00:00","updated_at":"2026-05-18T01:24:22.974022+00:00"}