{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I5IV6JABQHDJROTMNAZDRNMPWY","short_pith_number":"pith:I5IV6JAB","schema_version":"1.0","canonical_sha256":"47515f240181c698ba6c683238b58fb625e9f425d0a9345ec42174881fb074fe","source":{"kind":"arxiv","id":"2410.05441","version":1},"attestation_state":"computed","paper":{"title":"Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Raymond Zhang, Richard Combes","submitted_at":"2024-10-07T19:17:08Z","abstract_excerpt":"We consider Thompson Sampling (TS) for linear combinatorial semi-bandits and subgaussian rewards. We propose the first known TS whose finite-time regret does not scale exponentially with the dimension of the problem. We further show the \"mismatched sampling paradox\": A learner who knows the rewards distributions and samples from the correct posterior distribution can perform exponentially worse than a learner who does not know the rewards and simply samples from a well-chosen Gaussian posterior. The code used to generate the experiments is available at https://github.com/RaymZhang/CTS-Mismatch"},"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":"2410.05441","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-07T19:17:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4c5a8c80ffbf28ecdd0e33129d4fc9a89d889d4f6f32c927db500a022b9b69e6","abstract_canon_sha256":"3e4c6a3817897d690fa7c38430b0a23b4868978f6e603b193e456cfa5749a78f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:19.282205Z","signature_b64":"lJ4lvZEWywtPTXb6ANd9H0JNWwGI0P3ms6g1nzlO83OtFt1ACgD7cPHHz1VLeWSTW28dE+He/jTXyt6YnR2WDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47515f240181c698ba6c683238b58fb625e9f425d0a9345ec42174881fb074fe","last_reissued_at":"2026-07-05T09:17:19.281777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:19.281777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Raymond Zhang, Richard Combes","submitted_at":"2024-10-07T19:17:08Z","abstract_excerpt":"We consider Thompson Sampling (TS) for linear combinatorial semi-bandits and subgaussian rewards. We propose the first known TS whose finite-time regret does not scale exponentially with the dimension of the problem. We further show the \"mismatched sampling paradox\": A learner who knows the rewards distributions and samples from the correct posterior distribution can perform exponentially worse than a learner who does not know the rewards and simply samples from a well-chosen Gaussian posterior. The code used to generate the experiments is available at https://github.com/RaymZhang/CTS-Mismatch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05441","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/2410.05441/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":"2410.05441","created_at":"2026-07-05T09:17:19.281833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.05441v1","created_at":"2026-07-05T09:17:19.281833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05441","created_at":"2026-07-05T09:17:19.281833+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5IV6JABQHDJ","created_at":"2026-07-05T09:17:19.281833+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5IV6JABQHDJROTM","created_at":"2026-07-05T09:17:19.281833+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5IV6JAB","created_at":"2026-07-05T09:17:19.281833+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/I5IV6JABQHDJROTMNAZDRNMPWY","json":"https://pith.science/pith/I5IV6JABQHDJROTMNAZDRNMPWY.json","graph_json":"https://pith.science/api/pith-number/I5IV6JABQHDJROTMNAZDRNMPWY/graph.json","events_json":"https://pith.science/api/pith-number/I5IV6JABQHDJROTMNAZDRNMPWY/events.json","paper":"https://pith.science/paper/I5IV6JAB"},"agent_actions":{"view_html":"https://pith.science/pith/I5IV6JABQHDJROTMNAZDRNMPWY","download_json":"https://pith.science/pith/I5IV6JABQHDJROTMNAZDRNMPWY.json","view_paper":"https://pith.science/paper/I5IV6JAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.05441&json=true","fetch_graph":"https://pith.science/api/pith-number/I5IV6JABQHDJROTMNAZDRNMPWY/graph.json","fetch_events":"https://pith.science/api/pith-number/I5IV6JABQHDJROTMNAZDRNMPWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5IV6JABQHDJROTMNAZDRNMPWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5IV6JABQHDJROTMNAZDRNMPWY/action/storage_attestation","attest_author":"https://pith.science/pith/I5IV6JABQHDJROTMNAZDRNMPWY/action/author_attestation","sign_citation":"https://pith.science/pith/I5IV6JABQHDJROTMNAZDRNMPWY/action/citation_signature","submit_replication":"https://pith.science/pith/I5IV6JABQHDJROTMNAZDRNMPWY/action/replication_record"}},"created_at":"2026-07-05T09:17:19.281833+00:00","updated_at":"2026-07-05T09:17:19.281833+00:00"}