{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C5ALMRGCDXEWPWTJNDWLEXYHNH","short_pith_number":"pith:C5ALMRGC","schema_version":"1.0","canonical_sha256":"1740b644c21dc967da6968ecb25f0769e3be5b835f65f7e1cdd43534cf5f6871","source":{"kind":"arxiv","id":"2502.08870","version":2},"attestation_state":"computed","paper":{"title":"When and why randomised exploration works (in linear bandits)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ciara Pike-Burke, David Janz, Marc Abeille","submitted_at":"2025-02-13T00:49:28Z","abstract_excerpt":"We provide an approach for the analysis of randomised exploration algorithms like Thompson sampling that does not rely on forced optimism or posterior inflation. With this, we demonstrate that in the $d$-dimensional linear bandit setting, when the action space is smooth and strongly convex, randomised exploration algorithms enjoy an $n$-step regret bound of the order $O(d\\sqrt{n} \\log(n))$. Notably, this shows for the first time that there exist non-trivial linear bandit settings where Thompson sampling can achieve optimal dimension dependence in the regret."},"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":"2502.08870","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T00:49:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1a4b6a38b087459539c5e87b6a2260d760889e32eb3efedb6567e18d916b7061","abstract_canon_sha256":"b7a613255dd3a0e1ff188b19a0773108bd59af717786ff61e49fe647d0ff342c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:37.261837Z","signature_b64":"p8SqGWSAfQqYdVdq0iDeGSxoQ3K/+1MNDbQwlqH1ePRSpaDlIOgX1ZNIVK8+hqdN9yHjGjYvGm0Q13sAMjgxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1740b644c21dc967da6968ecb25f0769e3be5b835f65f7e1cdd43534cf5f6871","last_reissued_at":"2026-06-04T01:09:37.261231Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:37.261231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When and why randomised exploration works (in linear bandits)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ciara Pike-Burke, David Janz, Marc Abeille","submitted_at":"2025-02-13T00:49:28Z","abstract_excerpt":"We provide an approach for the analysis of randomised exploration algorithms like Thompson sampling that does not rely on forced optimism or posterior inflation. With this, we demonstrate that in the $d$-dimensional linear bandit setting, when the action space is smooth and strongly convex, randomised exploration algorithms enjoy an $n$-step regret bound of the order $O(d\\sqrt{n} \\log(n))$. Notably, this shows for the first time that there exist non-trivial linear bandit settings where Thompson sampling can achieve optimal dimension dependence in the regret."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08870","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/2502.08870/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":"2502.08870","created_at":"2026-06-04T01:09:37.261311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08870v2","created_at":"2026-06-04T01:09:37.261311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08870","created_at":"2026-06-04T01:09:37.261311+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5ALMRGCDXEW","created_at":"2026-06-04T01:09:37.261311+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5ALMRGCDXEWPWTJ","created_at":"2026-06-04T01:09:37.261311+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5ALMRGC","created_at":"2026-06-04T01:09:37.261311+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/C5ALMRGCDXEWPWTJNDWLEXYHNH","json":"https://pith.science/pith/C5ALMRGCDXEWPWTJNDWLEXYHNH.json","graph_json":"https://pith.science/api/pith-number/C5ALMRGCDXEWPWTJNDWLEXYHNH/graph.json","events_json":"https://pith.science/api/pith-number/C5ALMRGCDXEWPWTJNDWLEXYHNH/events.json","paper":"https://pith.science/paper/C5ALMRGC"},"agent_actions":{"view_html":"https://pith.science/pith/C5ALMRGCDXEWPWTJNDWLEXYHNH","download_json":"https://pith.science/pith/C5ALMRGCDXEWPWTJNDWLEXYHNH.json","view_paper":"https://pith.science/paper/C5ALMRGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08870&json=true","fetch_graph":"https://pith.science/api/pith-number/C5ALMRGCDXEWPWTJNDWLEXYHNH/graph.json","fetch_events":"https://pith.science/api/pith-number/C5ALMRGCDXEWPWTJNDWLEXYHNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5ALMRGCDXEWPWTJNDWLEXYHNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5ALMRGCDXEWPWTJNDWLEXYHNH/action/storage_attestation","attest_author":"https://pith.science/pith/C5ALMRGCDXEWPWTJNDWLEXYHNH/action/author_attestation","sign_citation":"https://pith.science/pith/C5ALMRGCDXEWPWTJNDWLEXYHNH/action/citation_signature","submit_replication":"https://pith.science/pith/C5ALMRGCDXEWPWTJNDWLEXYHNH/action/replication_record"}},"created_at":"2026-06-04T01:09:37.261311+00:00","updated_at":"2026-06-04T01:09:37.261311+00:00"}