{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FCIFGSUCVYKGPZ7H2PTYPFAS3Y","short_pith_number":"pith:FCIFGSUC","schema_version":"1.0","canonical_sha256":"2890534a82ae1467e7e7d3e7879412de29ad1157a3936cd3ca4a145e28056e6d","source":{"kind":"arxiv","id":"2302.10371","version":1},"attestation_state":"computed","paper":{"title":"Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Heyang Zhao, Jiafan He, Quanquan Gu, Tong Zhang","submitted_at":"2023-02-21T00:17:24Z","abstract_excerpt":"Recently, several studies (Zhou et al., 2021a; Zhang et al., 2021b; Kim et al., 2021; Zhou and Gu, 2022) have provided variance-dependent regret bounds for linear contextual bandits, which interpolates the regret for the worst-case regime and the deterministic reward regime. However, these algorithms are either computationally intractable or unable to handle unknown variance of the noise. In this paper, we present a novel solution to this open problem by proposing the first computationally efficient algorithm for linear bandits with heteroscedastic noise. Our algorithm is adaptive to the unkno"},"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":"2302.10371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-21T00:17:24Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"7df3cfeee3e8c0b57cb2140c0c46f233e8ab0c7c85c65d3430de09e53785fdcc","abstract_canon_sha256":"9c540c5943913ae4a30df3364add7a4f540c2d5896652c6860175181d5b225de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:38.468057Z","signature_b64":"KZz//h9lPZH9Q1o6ahOTPclt1Hs/Vqsh7yrarH+HCQJ38Pwl4edlHEsBP7b7rbwiyZXPLETprm6pf64ps/wNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2890534a82ae1467e7e7d3e7879412de29ad1157a3936cd3ca4a145e28056e6d","last_reissued_at":"2026-07-05T05:43:38.467522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:38.467522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Heyang Zhao, Jiafan He, Quanquan Gu, Tong Zhang","submitted_at":"2023-02-21T00:17:24Z","abstract_excerpt":"Recently, several studies (Zhou et al., 2021a; Zhang et al., 2021b; Kim et al., 2021; Zhou and Gu, 2022) have provided variance-dependent regret bounds for linear contextual bandits, which interpolates the regret for the worst-case regime and the deterministic reward regime. However, these algorithms are either computationally intractable or unable to handle unknown variance of the noise. In this paper, we present a novel solution to this open problem by proposing the first computationally efficient algorithm for linear bandits with heteroscedastic noise. Our algorithm is adaptive to the unkno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10371","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.10371/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":"2302.10371","created_at":"2026-07-05T05:43:38.467609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.10371v1","created_at":"2026-07-05T05:43:38.467609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10371","created_at":"2026-07-05T05:43:38.467609+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCIFGSUCVYKG","created_at":"2026-07-05T05:43:38.467609+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCIFGSUCVYKGPZ7H","created_at":"2026-07-05T05:43:38.467609+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCIFGSUC","created_at":"2026-07-05T05:43:38.467609+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/FCIFGSUCVYKGPZ7H2PTYPFAS3Y","json":"https://pith.science/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y.json","graph_json":"https://pith.science/api/pith-number/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/graph.json","events_json":"https://pith.science/api/pith-number/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/events.json","paper":"https://pith.science/paper/FCIFGSUC"},"agent_actions":{"view_html":"https://pith.science/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y","download_json":"https://pith.science/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y.json","view_paper":"https://pith.science/paper/FCIFGSUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.10371&json=true","fetch_graph":"https://pith.science/api/pith-number/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/action/storage_attestation","attest_author":"https://pith.science/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/action/author_attestation","sign_citation":"https://pith.science/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/action/citation_signature","submit_replication":"https://pith.science/pith/FCIFGSUCVYKGPZ7H2PTYPFAS3Y/action/replication_record"}},"created_at":"2026-07-05T05:43:38.467609+00:00","updated_at":"2026-07-05T05:43:38.467609+00:00"}