{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ECUIAQ3ZIBNVO4OYTX4BVIIOER","short_pith_number":"pith:ECUIAQ3Z","schema_version":"1.0","canonical_sha256":"20a8804379405b5771d89df81aa10e245eb707b5888eaba9e218fd9f9e1cde27","source":{"kind":"arxiv","id":"2307.07539","version":2},"attestation_state":"computed","paper":{"title":"On the Sublinear Regret of GP-UCB","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Aaditya Ramdas, Justin Whitehouse, Zhiwei Steven Wu","submitted_at":"2023-07-14T13:56:11Z","abstract_excerpt":"In the kernelized bandit problem, a learner aims to sequentially compute the optimum of a function lying in a reproducing kernel Hilbert space given only noisy evaluations at sequentially chosen points. In particular, the learner aims to minimize regret, which is a measure of the suboptimality of the choices made. Arguably the most popular algorithm is the Gaussian Process Upper Confidence Bound (GP-UCB) algorithm, which involves acting based on a simple linear estimator of the unknown function. Despite its popularity, existing analyses of GP-UCB give a suboptimal regret rate, which fails to b"},"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":"2307.07539","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-14T13:56:11Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"3c015e3847bea55d74e78cdb98adf7f58e3bcfb3bd2fbdf9cb692875080c997a","abstract_canon_sha256":"f0ffaefe9b57517a900d144636b7699d4cf2f09db3ca85103a2c919327e550a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:53.597789Z","signature_b64":"p0TybBwAHRR+6GOA2db4rNDoQGVhwjLyAJTcjkdYJAi5HonvOVSTAAr9EEn/slBL2vInWGFNeeGR7Y8MOZQiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20a8804379405b5771d89df81aa10e245eb707b5888eaba9e218fd9f9e1cde27","last_reissued_at":"2026-07-05T06:40:53.597122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:53.597122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Sublinear Regret of GP-UCB","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Aaditya Ramdas, Justin Whitehouse, Zhiwei Steven Wu","submitted_at":"2023-07-14T13:56:11Z","abstract_excerpt":"In the kernelized bandit problem, a learner aims to sequentially compute the optimum of a function lying in a reproducing kernel Hilbert space given only noisy evaluations at sequentially chosen points. In particular, the learner aims to minimize regret, which is a measure of the suboptimality of the choices made. Arguably the most popular algorithm is the Gaussian Process Upper Confidence Bound (GP-UCB) algorithm, which involves acting based on a simple linear estimator of the unknown function. Despite its popularity, existing analyses of GP-UCB give a suboptimal regret rate, which fails to b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07539","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/2307.07539/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":"2307.07539","created_at":"2026-07-05T06:40:53.597381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07539v2","created_at":"2026-07-05T06:40:53.597381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07539","created_at":"2026-07-05T06:40:53.597381+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECUIAQ3ZIBNV","created_at":"2026-07-05T06:40:53.597381+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECUIAQ3ZIBNVO4OY","created_at":"2026-07-05T06:40:53.597381+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECUIAQ3Z","created_at":"2026-07-05T06:40:53.597381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.01386","citing_title":"On the Suboptimality of GP-UCB under Polynomial Effective Optimism","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECUIAQ3ZIBNVO4OYTX4BVIIOER","json":"https://pith.science/pith/ECUIAQ3ZIBNVO4OYTX4BVIIOER.json","graph_json":"https://pith.science/api/pith-number/ECUIAQ3ZIBNVO4OYTX4BVIIOER/graph.json","events_json":"https://pith.science/api/pith-number/ECUIAQ3ZIBNVO4OYTX4BVIIOER/events.json","paper":"https://pith.science/paper/ECUIAQ3Z"},"agent_actions":{"view_html":"https://pith.science/pith/ECUIAQ3ZIBNVO4OYTX4BVIIOER","download_json":"https://pith.science/pith/ECUIAQ3ZIBNVO4OYTX4BVIIOER.json","view_paper":"https://pith.science/paper/ECUIAQ3Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07539&json=true","fetch_graph":"https://pith.science/api/pith-number/ECUIAQ3ZIBNVO4OYTX4BVIIOER/graph.json","fetch_events":"https://pith.science/api/pith-number/ECUIAQ3ZIBNVO4OYTX4BVIIOER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECUIAQ3ZIBNVO4OYTX4BVIIOER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECUIAQ3ZIBNVO4OYTX4BVIIOER/action/storage_attestation","attest_author":"https://pith.science/pith/ECUIAQ3ZIBNVO4OYTX4BVIIOER/action/author_attestation","sign_citation":"https://pith.science/pith/ECUIAQ3ZIBNVO4OYTX4BVIIOER/action/citation_signature","submit_replication":"https://pith.science/pith/ECUIAQ3ZIBNVO4OYTX4BVIIOER/action/replication_record"}},"created_at":"2026-07-05T06:40:53.597381+00:00","updated_at":"2026-07-05T06:40:53.597381+00:00"}