{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5OYQWODD64WMD2M7JK53GRE3AB","short_pith_number":"pith:5OYQWODD","schema_version":"1.0","canonical_sha256":"ebb10b3863f72cc1e99f4abbb3449b0062e1783ce407c032cc4e6fd21a770ad8","source":{"kind":"arxiv","id":"1903.05594","version":2},"attestation_state":"computed","paper":{"title":"Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Lazaric, Daniele Calandriello, Lorenzo Rosasco, Luigi Carratino, Michal Valko","submitted_at":"2019-03-13T16:50:40Z","abstract_excerpt":"Gaussian processes (GP) are a well studied Bayesian approach for the optimization of black-box functions. Despite their effectiveness in simple problems, GP-based algorithms hardly scale to high-dimensional functions, as their per-iteration time and space cost is at least quadratic in the number of dimensions $d$ and iterations $t$. Given a set of $A$ alternatives to choose from, the overall runtime $O(t^3A)$ is prohibitive. In this paper we introduce BKB (budgeted kernelized bandit), a new approximate GP algorithm for optimization under bandit feedback that achieves near-optimal regret (and h"},"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":"1903.05594","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-13T16:50:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7c2e204cc4164f14fb7ca477187016bf938f086bac61eebf466eca4d2b170e69","abstract_canon_sha256":"f345c6652baf37f4131677d179899e05bf61d4c6dfabe2f03772a4a13f4b0c60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:03.275960Z","signature_b64":"gmVSiEkkJsNHNcU9CiwdhltxwR2KmzN7lXgeW12h/ehZH2EG4PFOYJAI3QNprzcmDvsxCiPkUN71eEMTVqf7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebb10b3863f72cc1e99f4abbb3449b0062e1783ce407c032cc4e6fd21a770ad8","last_reissued_at":"2026-07-05T00:00:03.275540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:03.275540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Lazaric, Daniele Calandriello, Lorenzo Rosasco, Luigi Carratino, Michal Valko","submitted_at":"2019-03-13T16:50:40Z","abstract_excerpt":"Gaussian processes (GP) are a well studied Bayesian approach for the optimization of black-box functions. Despite their effectiveness in simple problems, GP-based algorithms hardly scale to high-dimensional functions, as their per-iteration time and space cost is at least quadratic in the number of dimensions $d$ and iterations $t$. Given a set of $A$ alternatives to choose from, the overall runtime $O(t^3A)$ is prohibitive. In this paper we introduce BKB (budgeted kernelized bandit), a new approximate GP algorithm for optimization under bandit feedback that achieves near-optimal regret (and h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05594","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/1903.05594/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":"1903.05594","created_at":"2026-07-05T00:00:03.275599+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.05594v2","created_at":"2026-07-05T00:00:03.275599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05594","created_at":"2026-07-05T00:00:03.275599+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OYQWODD64WM","created_at":"2026-07-05T00:00:03.275599+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OYQWODD64WMD2M7","created_at":"2026-07-05T00:00:03.275599+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OYQWODD","created_at":"2026-07-05T00:00:03.275599+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/5OYQWODD64WMD2M7JK53GRE3AB","json":"https://pith.science/pith/5OYQWODD64WMD2M7JK53GRE3AB.json","graph_json":"https://pith.science/api/pith-number/5OYQWODD64WMD2M7JK53GRE3AB/graph.json","events_json":"https://pith.science/api/pith-number/5OYQWODD64WMD2M7JK53GRE3AB/events.json","paper":"https://pith.science/paper/5OYQWODD"},"agent_actions":{"view_html":"https://pith.science/pith/5OYQWODD64WMD2M7JK53GRE3AB","download_json":"https://pith.science/pith/5OYQWODD64WMD2M7JK53GRE3AB.json","view_paper":"https://pith.science/paper/5OYQWODD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.05594&json=true","fetch_graph":"https://pith.science/api/pith-number/5OYQWODD64WMD2M7JK53GRE3AB/graph.json","fetch_events":"https://pith.science/api/pith-number/5OYQWODD64WMD2M7JK53GRE3AB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OYQWODD64WMD2M7JK53GRE3AB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OYQWODD64WMD2M7JK53GRE3AB/action/storage_attestation","attest_author":"https://pith.science/pith/5OYQWODD64WMD2M7JK53GRE3AB/action/author_attestation","sign_citation":"https://pith.science/pith/5OYQWODD64WMD2M7JK53GRE3AB/action/citation_signature","submit_replication":"https://pith.science/pith/5OYQWODD64WMD2M7JK53GRE3AB/action/replication_record"}},"created_at":"2026-07-05T00:00:03.275599+00:00","updated_at":"2026-07-05T00:00:03.275599+00:00"}