{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GPZGVKTXSQPE6NPJWF2R6VNXQ6","short_pith_number":"pith:GPZGVKTX","schema_version":"1.0","canonical_sha256":"33f26aaa77941e4f35e9b1751f55b787b1d56115c9e67634569eee6c9fcf513d","source":{"kind":"arxiv","id":"2111.03289","version":4},"attestation_state":"computed","paper":{"title":"Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Insoon Yang, Kwang-Sung Jun, Yeoneung Kim","submitted_at":"2021-11-05T06:47:27Z","abstract_excerpt":"In online learning problems, exploiting low variance plays an important role in obtaining tight performance guarantees yet is challenging because variances are often not known a priori. Recently, considerable progress has been made by Zhang et al. (2021) where they obtain a variance-adaptive regret bound for linear bandits without knowledge of the variances and a horizon-free regret bound for linear mixture Markov decision processes (MDPs). In this paper, we present novel analyses that improve their regret bounds significantly. For linear bandits, we achieve $\\tilde O(\\min\\{d\\sqrt{K}, d^{1.5}\\"},"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":"2111.03289","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-11-05T06:47:27Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"52a07a51530a240c7bbfbab05b7123b59e706e6cdd3c56154374297c90492601","abstract_canon_sha256":"195707cac88ee3a5ef65d0ef260489235c5b57bb366021d134519c32a95e2007"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:41.020772Z","signature_b64":"lur595+zpcZBTk4xBL3k08HmEMjBHHJtcw0ZPyQnATwIHO70s/PkHAhYozX8Ekozy5TrRUiWMXqYo7kG7UUbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33f26aaa77941e4f35e9b1751f55b787b1d56115c9e67634569eee6c9fcf513d","last_reissued_at":"2026-07-05T05:38:41.020353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:41.020353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Insoon Yang, Kwang-Sung Jun, Yeoneung Kim","submitted_at":"2021-11-05T06:47:27Z","abstract_excerpt":"In online learning problems, exploiting low variance plays an important role in obtaining tight performance guarantees yet is challenging because variances are often not known a priori. Recently, considerable progress has been made by Zhang et al. (2021) where they obtain a variance-adaptive regret bound for linear bandits without knowledge of the variances and a horizon-free regret bound for linear mixture Markov decision processes (MDPs). In this paper, we present novel analyses that improve their regret bounds significantly. For linear bandits, we achieve $\\tilde O(\\min\\{d\\sqrt{K}, d^{1.5}\\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03289","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/2111.03289/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":"2111.03289","created_at":"2026-07-05T05:38:41.020411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.03289v4","created_at":"2026-07-05T05:38:41.020411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03289","created_at":"2026-07-05T05:38:41.020411+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPZGVKTXSQPE","created_at":"2026-07-05T05:38:41.020411+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPZGVKTXSQPE6NPJ","created_at":"2026-07-05T05:38:41.020411+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPZGVKTX","created_at":"2026-07-05T05:38:41.020411+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02486","citing_title":"Catoni Contextual Bandits are Robust to Heavy-tailed Rewards","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPZGVKTXSQPE6NPJWF2R6VNXQ6","json":"https://pith.science/pith/GPZGVKTXSQPE6NPJWF2R6VNXQ6.json","graph_json":"https://pith.science/api/pith-number/GPZGVKTXSQPE6NPJWF2R6VNXQ6/graph.json","events_json":"https://pith.science/api/pith-number/GPZGVKTXSQPE6NPJWF2R6VNXQ6/events.json","paper":"https://pith.science/paper/GPZGVKTX"},"agent_actions":{"view_html":"https://pith.science/pith/GPZGVKTXSQPE6NPJWF2R6VNXQ6","download_json":"https://pith.science/pith/GPZGVKTXSQPE6NPJWF2R6VNXQ6.json","view_paper":"https://pith.science/paper/GPZGVKTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.03289&json=true","fetch_graph":"https://pith.science/api/pith-number/GPZGVKTXSQPE6NPJWF2R6VNXQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/GPZGVKTXSQPE6NPJWF2R6VNXQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPZGVKTXSQPE6NPJWF2R6VNXQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPZGVKTXSQPE6NPJWF2R6VNXQ6/action/storage_attestation","attest_author":"https://pith.science/pith/GPZGVKTXSQPE6NPJWF2R6VNXQ6/action/author_attestation","sign_citation":"https://pith.science/pith/GPZGVKTXSQPE6NPJWF2R6VNXQ6/action/citation_signature","submit_replication":"https://pith.science/pith/GPZGVKTXSQPE6NPJWF2R6VNXQ6/action/replication_record"}},"created_at":"2026-07-05T05:38:41.020411+00:00","updated_at":"2026-07-05T05:38:41.020411+00:00"}