{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HVL4PBEVKY35L3KSMAYWXRHXU7","short_pith_number":"pith:HVL4PBEV","schema_version":"1.0","canonical_sha256":"3d57c784955637d5ed5260316bc4f7a7fa1087c99fd5f2237d647a119c9db856","source":{"kind":"arxiv","id":"2012.11978","version":1},"attestation_state":"computed","paper":{"title":"Finding Global Minima via Kernel Approximations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Alessandro Rudi, Francis Bach, Ulysse Marteau-Ferey","submitted_at":"2020-12-22T12:59:30Z","abstract_excerpt":"We consider the global minimization of smooth functions based solely on function evaluations. Algorithms that achieve the optimal number of function evaluations for a given precision level typically rely on explicitly constructing an approximation of the function which is then minimized with algorithms that have exponential running-time complexity. In this paper, we consider an approach that jointly models the function to approximate and finds a global minimum. This is done by using infinite sums of square smooth functions and has strong links with polynomial sum-of-squares hierarchies. Levera"},"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":"2012.11978","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2020-12-22T12:59:30Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"279aa11eefbc258be15e503601cc659d2e1b5486a25af24508955248cff668ca","abstract_canon_sha256":"8802dfb73ccf6f06ff9c7da8c531937c38c5b8836bc44521d995a8fc9d3afb07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:01:23.457488Z","signature_b64":"OEDxvVMJwaISIE8ETCmuQ2z0r9oUhFpV1kOGbrWe7qVhgJaT6eLm2BJdVBEhbGgvuChTx9rN3n3erYYg8NC+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d57c784955637d5ed5260316bc4f7a7fa1087c99fd5f2237d647a119c9db856","last_reissued_at":"2026-07-05T02:01:23.457069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:01:23.457069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding Global Minima via Kernel Approximations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Alessandro Rudi, Francis Bach, Ulysse Marteau-Ferey","submitted_at":"2020-12-22T12:59:30Z","abstract_excerpt":"We consider the global minimization of smooth functions based solely on function evaluations. Algorithms that achieve the optimal number of function evaluations for a given precision level typically rely on explicitly constructing an approximation of the function which is then minimized with algorithms that have exponential running-time complexity. In this paper, we consider an approach that jointly models the function to approximate and finds a global minimum. This is done by using infinite sums of square smooth functions and has strong links with polynomial sum-of-squares hierarchies. Levera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11978","kind":"arxiv","version":1},"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/2012.11978/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":"2012.11978","created_at":"2026-07-05T02:01:23.457125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11978v1","created_at":"2026-07-05T02:01:23.457125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11978","created_at":"2026-07-05T02:01:23.457125+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVL4PBEVKY35","created_at":"2026-07-05T02:01:23.457125+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVL4PBEVKY35L3KS","created_at":"2026-07-05T02:01:23.457125+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVL4PBEV","created_at":"2026-07-05T02:01:23.457125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07767","citing_title":"Distributionally Faithful Imputation via Positive Semi-Definite Kernel Density Estimation","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2303.03237","citing_title":"Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HVL4PBEVKY35L3KSMAYWXRHXU7","json":"https://pith.science/pith/HVL4PBEVKY35L3KSMAYWXRHXU7.json","graph_json":"https://pith.science/api/pith-number/HVL4PBEVKY35L3KSMAYWXRHXU7/graph.json","events_json":"https://pith.science/api/pith-number/HVL4PBEVKY35L3KSMAYWXRHXU7/events.json","paper":"https://pith.science/paper/HVL4PBEV"},"agent_actions":{"view_html":"https://pith.science/pith/HVL4PBEVKY35L3KSMAYWXRHXU7","download_json":"https://pith.science/pith/HVL4PBEVKY35L3KSMAYWXRHXU7.json","view_paper":"https://pith.science/paper/HVL4PBEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11978&json=true","fetch_graph":"https://pith.science/api/pith-number/HVL4PBEVKY35L3KSMAYWXRHXU7/graph.json","fetch_events":"https://pith.science/api/pith-number/HVL4PBEVKY35L3KSMAYWXRHXU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVL4PBEVKY35L3KSMAYWXRHXU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVL4PBEVKY35L3KSMAYWXRHXU7/action/storage_attestation","attest_author":"https://pith.science/pith/HVL4PBEVKY35L3KSMAYWXRHXU7/action/author_attestation","sign_citation":"https://pith.science/pith/HVL4PBEVKY35L3KSMAYWXRHXU7/action/citation_signature","submit_replication":"https://pith.science/pith/HVL4PBEVKY35L3KSMAYWXRHXU7/action/replication_record"}},"created_at":"2026-07-05T02:01:23.457125+00:00","updated_at":"2026-07-05T02:01:23.457125+00:00"}