{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HHVJUVZAZFUWVCZ575UDO6WQCW","short_pith_number":"pith:HHVJUVZA","schema_version":"1.0","canonical_sha256":"39ea9a5720c9696a8b3dff68377ad01580a3843cd31687531baf3afff7afae37","source":{"kind":"arxiv","id":"1703.01968","version":3},"attestation_state":"computed","paper":{"title":"Max-value Entropy Search for Efficient Bayesian Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Stefanie Jegelka, Zi Wang","submitted_at":"2017-03-06T16:52:54Z","abstract_excerpt":"Entropy Search (ES) and Predictive Entropy Search (PES) are popular and empirically successful Bayesian Optimization techniques. Both rely on a compelling information-theoretic motivation, and maximize the information gained about the $\\arg\\max$ of the unknown function; yet, both are plagued by the expensive computation for estimating entropies. We propose a new criterion, Max-value Entropy Search (MES), that instead uses the information about the maximum function value. We show relations of MES to other Bayesian optimization methods, and establish a regret bound. We observe that MES maintains"},"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":"1703.01968","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-06T16:52:54Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"f2b8c16e3db3a172c90de754ca3a6150675bc2b8efef4fd6ecc6a0d1901002d2","abstract_canon_sha256":"ad9fb9950b82c9ec50d6f3a1b39a662ffd408f61064926218b2062e6ec138c82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:00.726591Z","signature_b64":"pmfxEoUHbNxA+Z6gxEpRKQkgN9IPlWkzU7NWifGdrQ0azG85f4yiDC7yrI2LSMzYLDqZU5AC8BgiI6meF/lWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39ea9a5720c9696a8b3dff68377ad01580a3843cd31687531baf3afff7afae37","last_reissued_at":"2026-05-18T00:09:00.725905Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:00.725905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Max-value Entropy Search for Efficient Bayesian Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Stefanie Jegelka, Zi Wang","submitted_at":"2017-03-06T16:52:54Z","abstract_excerpt":"Entropy Search (ES) and Predictive Entropy Search (PES) are popular and empirically successful Bayesian Optimization techniques. Both rely on a compelling information-theoretic motivation, and maximize the information gained about the $\\arg\\max$ of the unknown function; yet, both are plagued by the expensive computation for estimating entropies. We propose a new criterion, Max-value Entropy Search (MES), that instead uses the information about the maximum function value. We show relations of MES to other Bayesian optimization methods, and establish a regret bound. We observe that MES maintains"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01968","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1703.01968","created_at":"2026-05-18T00:09:00.726019+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.01968v3","created_at":"2026-05-18T00:09:00.726019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01968","created_at":"2026-05-18T00:09:00.726019+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHVJUVZAZFUW","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHVJUVZAZFUWVCZ5","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHVJUVZA","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.00865","citing_title":"Constrained Bayesian Optimisation with Multiple Information Sources","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HHVJUVZAZFUWVCZ575UDO6WQCW","json":"https://pith.science/pith/HHVJUVZAZFUWVCZ575UDO6WQCW.json","graph_json":"https://pith.science/api/pith-number/HHVJUVZAZFUWVCZ575UDO6WQCW/graph.json","events_json":"https://pith.science/api/pith-number/HHVJUVZAZFUWVCZ575UDO6WQCW/events.json","paper":"https://pith.science/paper/HHVJUVZA"},"agent_actions":{"view_html":"https://pith.science/pith/HHVJUVZAZFUWVCZ575UDO6WQCW","download_json":"https://pith.science/pith/HHVJUVZAZFUWVCZ575UDO6WQCW.json","view_paper":"https://pith.science/paper/HHVJUVZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.01968&json=true","fetch_graph":"https://pith.science/api/pith-number/HHVJUVZAZFUWVCZ575UDO6WQCW/graph.json","fetch_events":"https://pith.science/api/pith-number/HHVJUVZAZFUWVCZ575UDO6WQCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHVJUVZAZFUWVCZ575UDO6WQCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHVJUVZAZFUWVCZ575UDO6WQCW/action/storage_attestation","attest_author":"https://pith.science/pith/HHVJUVZAZFUWVCZ575UDO6WQCW/action/author_attestation","sign_citation":"https://pith.science/pith/HHVJUVZAZFUWVCZ575UDO6WQCW/action/citation_signature","submit_replication":"https://pith.science/pith/HHVJUVZAZFUWVCZ575UDO6WQCW/action/replication_record"}},"created_at":"2026-05-18T00:09:00.726019+00:00","updated_at":"2026-05-18T00:09:00.726019+00:00"}