{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HMIYIGCI7U3ADJKN3ETHTCE7ZI","short_pith_number":"pith:HMIYIGCI","schema_version":"1.0","canonical_sha256":"3b11841848fd3601a54dd92679889fca148e2fff6b64af015a648b849d66a122","source":{"kind":"arxiv","id":"2110.15688","version":1},"attestation_state":"computed","paper":{"title":"Variational Bayesian Optimistic Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Brendan O'Donoghue, Tor Lattimore","submitted_at":"2021-10-29T11:28:29Z","abstract_excerpt":"We consider online sequential decision problems where an agent must balance exploration and exploitation. We derive a set of Bayesian `optimistic' policies which, in the stochastic multi-armed bandit case, includes the Thompson sampling policy. We provide a new analysis showing that any algorithm producing policies in the optimistic set enjoys $\\tilde O(\\sqrt{AT})$ Bayesian regret for a problem with $A$ actions after $T$ rounds. We extend the regret analysis for optimistic policies to bilinear saddle-point problems which include zero-sum matrix games and constrained bandits as special cases. I"},"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":"2110.15688","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T11:28:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e1b8bea33082e59f0aeeee0e1855075416dd023959e214f61e5a5beeb185d3d1","abstract_canon_sha256":"187b445a06d87c246b75072db83d6d84bf9b693b171eceb003d2ce135ba9bfac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:12.797107Z","signature_b64":"LFuuZcGTjw+NW1+G9LDWw5p10fNvo4Nsypga8lcOWE3uF0SqoQoiL6YnKhcw04r7AcHbQeVKnSqINEwQmR15Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b11841848fd3601a54dd92679889fca148e2fff6b64af015a648b849d66a122","last_reissued_at":"2026-07-05T03:27:12.796647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:12.796647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Bayesian Optimistic Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Brendan O'Donoghue, Tor Lattimore","submitted_at":"2021-10-29T11:28:29Z","abstract_excerpt":"We consider online sequential decision problems where an agent must balance exploration and exploitation. We derive a set of Bayesian `optimistic' policies which, in the stochastic multi-armed bandit case, includes the Thompson sampling policy. We provide a new analysis showing that any algorithm producing policies in the optimistic set enjoys $\\tilde O(\\sqrt{AT})$ Bayesian regret for a problem with $A$ actions after $T$ rounds. We extend the regret analysis for optimistic policies to bilinear saddle-point problems which include zero-sum matrix games and constrained bandits as special cases. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15688","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/2110.15688/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":"2110.15688","created_at":"2026-07-05T03:27:12.796726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.15688v1","created_at":"2026-07-05T03:27:12.796726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15688","created_at":"2026-07-05T03:27:12.796726+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMIYIGCI7U3A","created_at":"2026-07-05T03:27:12.796726+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMIYIGCI7U3ADJKN","created_at":"2026-07-05T03:27:12.796726+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMIYIGCI","created_at":"2026-07-05T03:27:12.796726+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/HMIYIGCI7U3ADJKN3ETHTCE7ZI","json":"https://pith.science/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI.json","graph_json":"https://pith.science/api/pith-number/HMIYIGCI7U3ADJKN3ETHTCE7ZI/graph.json","events_json":"https://pith.science/api/pith-number/HMIYIGCI7U3ADJKN3ETHTCE7ZI/events.json","paper":"https://pith.science/paper/HMIYIGCI"},"agent_actions":{"view_html":"https://pith.science/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI","download_json":"https://pith.science/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI.json","view_paper":"https://pith.science/paper/HMIYIGCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.15688&json=true","fetch_graph":"https://pith.science/api/pith-number/HMIYIGCI7U3ADJKN3ETHTCE7ZI/graph.json","fetch_events":"https://pith.science/api/pith-number/HMIYIGCI7U3ADJKN3ETHTCE7ZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI/action/storage_attestation","attest_author":"https://pith.science/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI/action/author_attestation","sign_citation":"https://pith.science/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI/action/citation_signature","submit_replication":"https://pith.science/pith/HMIYIGCI7U3ADJKN3ETHTCE7ZI/action/replication_record"}},"created_at":"2026-07-05T03:27:12.796726+00:00","updated_at":"2026-07-05T03:27:12.796726+00:00"}