{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7XQAFWTPDVLZF5OHGF7OKDD3GV","short_pith_number":"pith:7XQAFWTP","schema_version":"1.0","canonical_sha256":"fde002da6f1d5792f5c7317ee50c7b354a54701fc9332eee1f30c822c7766236","source":{"kind":"arxiv","id":"2107.12102","version":1},"attestation_state":"computed","paper":{"title":"Global optimization using random embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Adilet Otemissov, Coralia Cartis, Estelle Massart","submitted_at":"2021-07-26T10:45:49Z","abstract_excerpt":"We propose a random-subspace algorithmic framework for global optimization of Lipschitz-continuous objectives, and analyse its convergence using novel tools from conic integral geometry. X-REGO randomly projects, in a sequential or simultaneous manner, the high-dimensional original problem into low-dimensional subproblems that can then be solved with any global, or even local, optimization solver. We estimate the probability that the randomly-embedded subproblem shares (approximately) the same global optimum as the original problem. This success probability is then used to show convergence of "},"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":"2107.12102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-07-26T10:45:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ada205538f1d4ccc00660055b7cbb788bc95e76e3ae1c5fe5fcd1419d38b4b4d","abstract_canon_sha256":"c8e75f713afa2cc7688c4139261865c0bbf9229d2f4a89f0d360072b95f49917"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:55.803105Z","signature_b64":"ax1JNs6a5SrvJQw2KLLbp5IMgoVJLYtQq1KKnPIPmJwJtslwK6q9hkjYnU76mNeyy8ynFwY0jkEvvyNM2WTPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fde002da6f1d5792f5c7317ee50c7b354a54701fc9332eee1f30c822c7766236","last_reissued_at":"2026-07-05T03:00:55.802552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:55.802552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global optimization using random embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Adilet Otemissov, Coralia Cartis, Estelle Massart","submitted_at":"2021-07-26T10:45:49Z","abstract_excerpt":"We propose a random-subspace algorithmic framework for global optimization of Lipschitz-continuous objectives, and analyse its convergence using novel tools from conic integral geometry. X-REGO randomly projects, in a sequential or simultaneous manner, the high-dimensional original problem into low-dimensional subproblems that can then be solved with any global, or even local, optimization solver. We estimate the probability that the randomly-embedded subproblem shares (approximately) the same global optimum as the original problem. This success probability is then used to show convergence of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.12102","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/2107.12102/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":"2107.12102","created_at":"2026-07-05T03:00:55.802612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.12102v1","created_at":"2026-07-05T03:00:55.802612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.12102","created_at":"2026-07-05T03:00:55.802612+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XQAFWTPDVLZ","created_at":"2026-07-05T03:00:55.802612+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XQAFWTPDVLZF5OH","created_at":"2026-07-05T03:00:55.802612+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XQAFWTP","created_at":"2026-07-05T03:00:55.802612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.09183","citing_title":"Dimensionality Reduction Techniques for Global Bayesian Optimisation","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7XQAFWTPDVLZF5OHGF7OKDD3GV","json":"https://pith.science/pith/7XQAFWTPDVLZF5OHGF7OKDD3GV.json","graph_json":"https://pith.science/api/pith-number/7XQAFWTPDVLZF5OHGF7OKDD3GV/graph.json","events_json":"https://pith.science/api/pith-number/7XQAFWTPDVLZF5OHGF7OKDD3GV/events.json","paper":"https://pith.science/paper/7XQAFWTP"},"agent_actions":{"view_html":"https://pith.science/pith/7XQAFWTPDVLZF5OHGF7OKDD3GV","download_json":"https://pith.science/pith/7XQAFWTPDVLZF5OHGF7OKDD3GV.json","view_paper":"https://pith.science/paper/7XQAFWTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.12102&json=true","fetch_graph":"https://pith.science/api/pith-number/7XQAFWTPDVLZF5OHGF7OKDD3GV/graph.json","fetch_events":"https://pith.science/api/pith-number/7XQAFWTPDVLZF5OHGF7OKDD3GV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XQAFWTPDVLZF5OHGF7OKDD3GV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XQAFWTPDVLZF5OHGF7OKDD3GV/action/storage_attestation","attest_author":"https://pith.science/pith/7XQAFWTPDVLZF5OHGF7OKDD3GV/action/author_attestation","sign_citation":"https://pith.science/pith/7XQAFWTPDVLZF5OHGF7OKDD3GV/action/citation_signature","submit_replication":"https://pith.science/pith/7XQAFWTPDVLZF5OHGF7OKDD3GV/action/replication_record"}},"created_at":"2026-07-05T03:00:55.802612+00:00","updated_at":"2026-07-05T03:00:55.802612+00:00"}