{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HMIYIGCI7U3ADJKN3ETHTCE7ZI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"187b445a06d87c246b75072db83d6d84bf9b693b171eceb003d2ce135ba9bfac","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T11:28:29Z","title_canon_sha256":"e1b8bea33082e59f0aeeee0e1855075416dd023959e214f61e5a5beeb185d3d1"},"schema_version":"1.0","source":{"id":"2110.15688","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.15688","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"arxiv_version","alias_value":"2110.15688v1","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15688","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"pith_short_12","alias_value":"HMIYIGCI7U3A","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"pith_short_16","alias_value":"HMIYIGCI7U3ADJKN","created_at":"2026-07-05T03:27:12Z"},{"alias_kind":"pith_short_8","alias_value":"HMIYIGCI","created_at":"2026-07-05T03:27:12Z"}],"graph_snapshots":[{"event_id":"sha256:16c11f16c61658a825417d1f85806c927c151066005245b834c27fe339b51968","target":"graph","created_at":"2026-07-05T03:27:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.15688/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Brendan O'Donoghue, Tor Lattimore","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T11:28:29Z","title":"Variational Bayesian Optimistic Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15688","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6c615f25c17cae9557671e1b4b2b5ad3595f2486a8b8cd0a2443da1a202a0eed","target":"record","created_at":"2026-07-05T03:27:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"187b445a06d87c246b75072db83d6d84bf9b693b171eceb003d2ce135ba9bfac","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T11:28:29Z","title_canon_sha256":"e1b8bea33082e59f0aeeee0e1855075416dd023959e214f61e5a5beeb185d3d1"},"schema_version":"1.0","source":{"id":"2110.15688","kind":"arxiv","version":1}},"canonical_sha256":"3b11841848fd3601a54dd92679889fca148e2fff6b64af015a648b849d66a122","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b11841848fd3601a54dd92679889fca148e2fff6b64af015a648b849d66a122","first_computed_at":"2026-07-05T03:27:12.796647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:12.796647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LFuuZcGTjw+NW1+G9LDWw5p10fNvo4Nsypga8lcOWE3uF0SqoQoiL6YnKhcw04r7AcHbQeVKnSqINEwQmR15Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:12.797107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.15688","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c615f25c17cae9557671e1b4b2b5ad3595f2486a8b8cd0a2443da1a202a0eed","sha256:16c11f16c61658a825417d1f85806c927c151066005245b834c27fe339b51968"],"state_sha256":"0828a124e0b72a1e8b0d21f7e6ae53d157cd3afd0070507897fa2cf0155799ea"}