{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LOTIHLVFEJLIHYN2GTOGNW5TOY","short_pith_number":"pith:LOTIHLVF","schema_version":"1.0","canonical_sha256":"5ba683aea5225683e1ba34dc66dbb37605084843e4db8cb67a4afeb5523791e9","source":{"kind":"arxiv","id":"2008.08757","version":2},"attestation_state":"computed","paper":{"title":"On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","math.OC"],"primary_cat":"stat.ML","authors_text":"Jonathan Scarlett, Xu Cai","submitted_at":"2020-08-20T03:48:14Z","abstract_excerpt":"In this paper, we consider algorithm-independent lower bounds for the problem of black-box optimization of functions having a bounded norm is some Reproducing Kernel Hilbert Space (RKHS), which can be viewed as a non-Bayesian Gaussian process bandit problem. In the standard noisy setting, we provide a novel proof technique for deriving lower bounds on the regret, with benefits including simplicity, versatility, and an improved dependence on the error probability. In a robust setting in which every sampled point may be perturbed by a suitably-constrained adversary, we provide a novel lower boun"},"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":"2008.08757","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-08-20T03:48:14Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.OC"],"title_canon_sha256":"c6264bdb0cc5be97298b62d9a65e498b8d52ed62809ff8d505f4f8673abf2485","abstract_canon_sha256":"cfdb4c9eb7e58fc2ed1308129e1b1cafdbc282da57325c2820d0c493ae99ce09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:26.442212Z","signature_b64":"yTqJy/r/sbSIGg3rfa3KxbmU5LWz1MqVIOJnflvK/WeX06vtNHHv/05fkWdC/0DnOIX5mmwqe96XZVgYPPIGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ba683aea5225683e1ba34dc66dbb37605084843e4db8cb67a4afeb5523791e9","last_reissued_at":"2026-07-05T02:42:26.441730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:26.441730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","math.OC"],"primary_cat":"stat.ML","authors_text":"Jonathan Scarlett, Xu Cai","submitted_at":"2020-08-20T03:48:14Z","abstract_excerpt":"In this paper, we consider algorithm-independent lower bounds for the problem of black-box optimization of functions having a bounded norm is some Reproducing Kernel Hilbert Space (RKHS), which can be viewed as a non-Bayesian Gaussian process bandit problem. In the standard noisy setting, we provide a novel proof technique for deriving lower bounds on the regret, with benefits including simplicity, versatility, and an improved dependence on the error probability. In a robust setting in which every sampled point may be perturbed by a suitably-constrained adversary, we provide a novel lower boun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.08757","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/2008.08757/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":"2008.08757","created_at":"2026-07-05T02:42:26.441779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.08757v2","created_at":"2026-07-05T02:42:26.441779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.08757","created_at":"2026-07-05T02:42:26.441779+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOTIHLVFEJLI","created_at":"2026-07-05T02:42:26.441779+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOTIHLVFEJLIHYN2","created_at":"2026-07-05T02:42:26.441779+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOTIHLVF","created_at":"2026-07-05T02:42:26.441779+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.01328","citing_title":"Efficient and Principled Scientific Discovery through Bayesian Optimization: A Tutorial","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LOTIHLVFEJLIHYN2GTOGNW5TOY","json":"https://pith.science/pith/LOTIHLVFEJLIHYN2GTOGNW5TOY.json","graph_json":"https://pith.science/api/pith-number/LOTIHLVFEJLIHYN2GTOGNW5TOY/graph.json","events_json":"https://pith.science/api/pith-number/LOTIHLVFEJLIHYN2GTOGNW5TOY/events.json","paper":"https://pith.science/paper/LOTIHLVF"},"agent_actions":{"view_html":"https://pith.science/pith/LOTIHLVFEJLIHYN2GTOGNW5TOY","download_json":"https://pith.science/pith/LOTIHLVFEJLIHYN2GTOGNW5TOY.json","view_paper":"https://pith.science/paper/LOTIHLVF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.08757&json=true","fetch_graph":"https://pith.science/api/pith-number/LOTIHLVFEJLIHYN2GTOGNW5TOY/graph.json","fetch_events":"https://pith.science/api/pith-number/LOTIHLVFEJLIHYN2GTOGNW5TOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOTIHLVFEJLIHYN2GTOGNW5TOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOTIHLVFEJLIHYN2GTOGNW5TOY/action/storage_attestation","attest_author":"https://pith.science/pith/LOTIHLVFEJLIHYN2GTOGNW5TOY/action/author_attestation","sign_citation":"https://pith.science/pith/LOTIHLVFEJLIHYN2GTOGNW5TOY/action/citation_signature","submit_replication":"https://pith.science/pith/LOTIHLVFEJLIHYN2GTOGNW5TOY/action/replication_record"}},"created_at":"2026-07-05T02:42:26.441779+00:00","updated_at":"2026-07-05T02:42:26.441779+00:00"}