{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EEJHB4NDAOKB5QC6PZONCW4DCE","short_pith_number":"pith:EEJHB4ND","schema_version":"1.0","canonical_sha256":"211270f1a303941ec05e7e5cd15b83113df4c2db57d5f26387b1a1538dae5f88","source":{"kind":"arxiv","id":"2110.08627","version":3},"attestation_state":"computed","paper":{"title":"Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Vincent Y. F. Tan, Wang Chi Cheung, Zixin Zhong","submitted_at":"2021-10-16T17:52:32Z","abstract_excerpt":"We study the Pareto frontier of two archetypal objectives in multi-armed bandits, namely, regret minimization (RM) and best arm identification (BAI) with a fixed horizon. It is folklore that the balance between exploitation and exploration is crucial for both RM and BAI, but exploration is more critical in achieving the optimal performance for the latter objective. To this end, we design and analyze the BoBW-lil'UCB$(\\gamma)$ algorithm. Complementarily, by establishing lower bounds on the regret achievable by any algorithm with a given BAI failure probability, we show that (i) no algorithm can"},"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":"2110.08627","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-16T17:52:32Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"b6405c075c99fb24aa8b164ab30fdff6129bbc1217d585d62b21e643a6ab8c5d","abstract_canon_sha256":"8a2e0922413d48e9b7879e8bf5a01607955f01e69fe98fd7c0df0eae422b60cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:58.220264Z","signature_b64":"O/7T3p8r6nT1mBc5vbm6cz7kvLwGpdt6G7yFaPFdF74L/i+6sTKGHlhem3ftn0RTdTNE+Y2L+RaXLFVYhZtQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"211270f1a303941ec05e7e5cd15b83113df4c2db57d5f26387b1a1538dae5f88","last_reissued_at":"2026-07-05T06:18:58.219827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:58.219827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Vincent Y. F. Tan, Wang Chi Cheung, Zixin Zhong","submitted_at":"2021-10-16T17:52:32Z","abstract_excerpt":"We study the Pareto frontier of two archetypal objectives in multi-armed bandits, namely, regret minimization (RM) and best arm identification (BAI) with a fixed horizon. It is folklore that the balance between exploitation and exploration is crucial for both RM and BAI, but exploration is more critical in achieving the optimal performance for the latter objective. To this end, we design and analyze the BoBW-lil'UCB$(\\gamma)$ algorithm. Complementarily, by establishing lower bounds on the regret achievable by any algorithm with a given BAI failure probability, we show that (i) no algorithm can"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08627","kind":"arxiv","version":3},"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/2110.08627/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":"2110.08627","created_at":"2026-07-05T06:18:58.219884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.08627v3","created_at":"2026-07-05T06:18:58.219884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08627","created_at":"2026-07-05T06:18:58.219884+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEJHB4NDAOKB","created_at":"2026-07-05T06:18:58.219884+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEJHB4NDAOKB5QC6","created_at":"2026-07-05T06:18:58.219884+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEJHB4ND","created_at":"2026-07-05T06:18:58.219884+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.05145","citing_title":"From Restless to Contextual: A Thresholding Bandit Reformulation For Finite-horizon Improvement","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEJHB4NDAOKB5QC6PZONCW4DCE","json":"https://pith.science/pith/EEJHB4NDAOKB5QC6PZONCW4DCE.json","graph_json":"https://pith.science/api/pith-number/EEJHB4NDAOKB5QC6PZONCW4DCE/graph.json","events_json":"https://pith.science/api/pith-number/EEJHB4NDAOKB5QC6PZONCW4DCE/events.json","paper":"https://pith.science/paper/EEJHB4ND"},"agent_actions":{"view_html":"https://pith.science/pith/EEJHB4NDAOKB5QC6PZONCW4DCE","download_json":"https://pith.science/pith/EEJHB4NDAOKB5QC6PZONCW4DCE.json","view_paper":"https://pith.science/paper/EEJHB4ND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.08627&json=true","fetch_graph":"https://pith.science/api/pith-number/EEJHB4NDAOKB5QC6PZONCW4DCE/graph.json","fetch_events":"https://pith.science/api/pith-number/EEJHB4NDAOKB5QC6PZONCW4DCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEJHB4NDAOKB5QC6PZONCW4DCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEJHB4NDAOKB5QC6PZONCW4DCE/action/storage_attestation","attest_author":"https://pith.science/pith/EEJHB4NDAOKB5QC6PZONCW4DCE/action/author_attestation","sign_citation":"https://pith.science/pith/EEJHB4NDAOKB5QC6PZONCW4DCE/action/citation_signature","submit_replication":"https://pith.science/pith/EEJHB4NDAOKB5QC6PZONCW4DCE/action/replication_record"}},"created_at":"2026-07-05T06:18:58.219884+00:00","updated_at":"2026-07-05T06:18:58.219884+00:00"}