{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FVDKO3PYZP2KNZWCAYJMZAGTCW","short_pith_number":"pith:FVDKO3PY","schema_version":"1.0","canonical_sha256":"2d46a76df8cbf4a6e6c20612cc80d315b952e757bb9fd0800bbf9187ac47d31a","source":{"kind":"arxiv","id":"2101.12745","version":4},"attestation_state":"computed","paper":{"title":"Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaqi Yang, Simon S. Du, Xiangyang Ji, Zihan Zhang","submitted_at":"2021-01-29T18:57:52Z","abstract_excerpt":"This paper presents new \\emph{variance-aware} confidence sets for linear bandits and linear mixture Markov Decision Processes (MDPs). With the new confidence sets, we obtain the follow regret bounds: For linear bandits, we obtain an $\\tilde{O}(poly(d)\\sqrt{1 + \\sum_{k=1}^{K}\\sigma_k^2})$ data-dependent regret bound, where $d$ is the feature dimension, $K$ is the number of rounds, and $\\sigma_k^2$ is the \\emph{unknown} variance of the reward at the $k$-th round. This is the first regret bound that only scales with the variance and the dimension but \\emph{no explicit polynomial dependency on $K$"},"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":"2101.12745","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-29T18:57:52Z","cross_cats_sorted":[],"title_canon_sha256":"e17a06bdd67e1c6ebd9dfb17d22e07b56a57795bdebbd0ddbbd4cbf395959aa6","abstract_canon_sha256":"7fef492109580c168e664b96e47dbfd5a8f2cf980d5c5d5569f76c2b3a7dc9e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:58.539800Z","signature_b64":"7ymgR36HYkMRFIEqS2Ok9OplnDPCY7bmqeOP6yolW0thV7E3WO5DC6hKP93/gUxWBo3713TzRGoeeemWOxWNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d46a76df8cbf4a6e6c20612cc80d315b952e757bb9fd0800bbf9187ac47d31a","last_reissued_at":"2026-07-05T03:26:58.539296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:58.539296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaqi Yang, Simon S. Du, Xiangyang Ji, Zihan Zhang","submitted_at":"2021-01-29T18:57:52Z","abstract_excerpt":"This paper presents new \\emph{variance-aware} confidence sets for linear bandits and linear mixture Markov Decision Processes (MDPs). With the new confidence sets, we obtain the follow regret bounds: For linear bandits, we obtain an $\\tilde{O}(poly(d)\\sqrt{1 + \\sum_{k=1}^{K}\\sigma_k^2})$ data-dependent regret bound, where $d$ is the feature dimension, $K$ is the number of rounds, and $\\sigma_k^2$ is the \\emph{unknown} variance of the reward at the $k$-th round. This is the first regret bound that only scales with the variance and the dimension but \\emph{no explicit polynomial dependency on $K$"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.12745","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/2101.12745/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":"2101.12745","created_at":"2026-07-05T03:26:58.539368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.12745v4","created_at":"2026-07-05T03:26:58.539368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.12745","created_at":"2026-07-05T03:26:58.539368+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVDKO3PYZP2K","created_at":"2026-07-05T03:26:58.539368+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVDKO3PYZP2KNZWC","created_at":"2026-07-05T03:26:58.539368+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVDKO3PY","created_at":"2026-07-05T03:26:58.539368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07218","citing_title":"Improved Model-based Reinforcement Learning with Smooth Kernels","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FVDKO3PYZP2KNZWCAYJMZAGTCW","json":"https://pith.science/pith/FVDKO3PYZP2KNZWCAYJMZAGTCW.json","graph_json":"https://pith.science/api/pith-number/FVDKO3PYZP2KNZWCAYJMZAGTCW/graph.json","events_json":"https://pith.science/api/pith-number/FVDKO3PYZP2KNZWCAYJMZAGTCW/events.json","paper":"https://pith.science/paper/FVDKO3PY"},"agent_actions":{"view_html":"https://pith.science/pith/FVDKO3PYZP2KNZWCAYJMZAGTCW","download_json":"https://pith.science/pith/FVDKO3PYZP2KNZWCAYJMZAGTCW.json","view_paper":"https://pith.science/paper/FVDKO3PY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.12745&json=true","fetch_graph":"https://pith.science/api/pith-number/FVDKO3PYZP2KNZWCAYJMZAGTCW/graph.json","fetch_events":"https://pith.science/api/pith-number/FVDKO3PYZP2KNZWCAYJMZAGTCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVDKO3PYZP2KNZWCAYJMZAGTCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVDKO3PYZP2KNZWCAYJMZAGTCW/action/storage_attestation","attest_author":"https://pith.science/pith/FVDKO3PYZP2KNZWCAYJMZAGTCW/action/author_attestation","sign_citation":"https://pith.science/pith/FVDKO3PYZP2KNZWCAYJMZAGTCW/action/citation_signature","submit_replication":"https://pith.science/pith/FVDKO3PYZP2KNZWCAYJMZAGTCW/action/replication_record"}},"created_at":"2026-07-05T03:26:58.539368+00:00","updated_at":"2026-07-05T03:26:58.539368+00:00"}