{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PRNOEO4NNM5YIIT3MTYE77BT5B","short_pith_number":"pith:PRNOEO4N","schema_version":"1.0","canonical_sha256":"7c5ae23b8d6b3b84227b64f04ffc33e8672e62acfa6caa1c83c30333f7bbbefe","source":{"kind":"arxiv","id":"2410.12713","version":2},"attestation_state":"computed","paper":{"title":"How Does Variance Shape the Regret in Contextual Bandits?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Chen-Yu Wei, Jian Qian, Zeyu Jia","submitted_at":"2024-10-16T16:20:07Z","abstract_excerpt":"We consider realizable contextual bandits with general function approximation, investigating how small reward variance can lead to better-than-minimax regret bounds. Unlike in minimax bounds, we show that the eluder dimension $d_\\text{elu}$$-$a complexity measure of the function class$-$plays a crucial role in variance-dependent bounds. We consider two types of adversary:\n  (1) Weak adversary: The adversary sets the reward variance before observing the learner's action. In this setting, we prove that a regret of $\\Omega(\\sqrt{\\min\\{A,d_\\text{elu}\\}\\Lambda}+d_\\text{elu})$ is unavoidable when $d"},"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":"2410.12713","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T16:20:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"56ecd1524427ec16245d8656039cb9a6189e409b060ecdfada93cd2b777c168a","abstract_canon_sha256":"07b6ae06a83e078182054525a07984e78ebf5f4ee1958e6c81bdc9fa7cc3e04d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:02.777887Z","signature_b64":"fJYtdditOXAP+pXRXIssJnv39wyUipf6KFca1WknFUzS+f33GIHMMgBnqYQWhVllmRycaA+w7HLC8A0oz8w+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c5ae23b8d6b3b84227b64f04ffc33e8672e62acfa6caa1c83c30333f7bbbefe","last_reissued_at":"2026-07-05T09:41:02.777437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:02.777437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Does Variance Shape the Regret in Contextual Bandits?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Chen-Yu Wei, Jian Qian, Zeyu Jia","submitted_at":"2024-10-16T16:20:07Z","abstract_excerpt":"We consider realizable contextual bandits with general function approximation, investigating how small reward variance can lead to better-than-minimax regret bounds. Unlike in minimax bounds, we show that the eluder dimension $d_\\text{elu}$$-$a complexity measure of the function class$-$plays a crucial role in variance-dependent bounds. We consider two types of adversary:\n  (1) Weak adversary: The adversary sets the reward variance before observing the learner's action. In this setting, we prove that a regret of $\\Omega(\\sqrt{\\min\\{A,d_\\text{elu}\\}\\Lambda}+d_\\text{elu})$ is unavoidable when $d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12713","kind":"arxiv","version":2},"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/2410.12713/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":"2410.12713","created_at":"2026-07-05T09:41:02.777507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12713v2","created_at":"2026-07-05T09:41:02.777507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12713","created_at":"2026-07-05T09:41:02.777507+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRNOEO4NNM5Y","created_at":"2026-07-05T09:41:02.777507+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRNOEO4NNM5YIIT3","created_at":"2026-07-05T09:41:02.777507+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRNOEO4N","created_at":"2026-07-05T09:41:02.777507+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/PRNOEO4NNM5YIIT3MTYE77BT5B","json":"https://pith.science/pith/PRNOEO4NNM5YIIT3MTYE77BT5B.json","graph_json":"https://pith.science/api/pith-number/PRNOEO4NNM5YIIT3MTYE77BT5B/graph.json","events_json":"https://pith.science/api/pith-number/PRNOEO4NNM5YIIT3MTYE77BT5B/events.json","paper":"https://pith.science/paper/PRNOEO4N"},"agent_actions":{"view_html":"https://pith.science/pith/PRNOEO4NNM5YIIT3MTYE77BT5B","download_json":"https://pith.science/pith/PRNOEO4NNM5YIIT3MTYE77BT5B.json","view_paper":"https://pith.science/paper/PRNOEO4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12713&json=true","fetch_graph":"https://pith.science/api/pith-number/PRNOEO4NNM5YIIT3MTYE77BT5B/graph.json","fetch_events":"https://pith.science/api/pith-number/PRNOEO4NNM5YIIT3MTYE77BT5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRNOEO4NNM5YIIT3MTYE77BT5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRNOEO4NNM5YIIT3MTYE77BT5B/action/storage_attestation","attest_author":"https://pith.science/pith/PRNOEO4NNM5YIIT3MTYE77BT5B/action/author_attestation","sign_citation":"https://pith.science/pith/PRNOEO4NNM5YIIT3MTYE77BT5B/action/citation_signature","submit_replication":"https://pith.science/pith/PRNOEO4NNM5YIIT3MTYE77BT5B/action/replication_record"}},"created_at":"2026-07-05T09:41:02.777507+00:00","updated_at":"2026-07-05T09:41:02.777507+00:00"}