{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:YD2OMMHDLVHVA4SGGER4R6YUJI","short_pith_number":"pith:YD2OMMHD","schema_version":"1.0","canonical_sha256":"c0f4e630e35d4f5072463123c8fb144a1fa7fc6acfe9adf9fa14c43c1d6e835a","source":{"kind":"arxiv","id":"1604.08459","version":1},"attestation_state":"computed","paper":{"title":"Noisy Optimization: Fast Convergence Rates with Comparison-Based Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"LRI, Marie-Liesse Cauwet (INRIA, Olivier Teytaud (LRI, TAO)","submitted_at":"2016-04-28T15:18:07Z","abstract_excerpt":"Derivative Free Optimization is known to be an efficient and robust method to tackle the black-box optimization problem. When it comes to noisy functions, classical comparison-based algorithms are slower than gradient-based algorithms. For quadratic functions, Evolutionary Algorithms without large mutations have a simple regret at best $O(1/ \\sqrt{N})$ when $N$ is the number of function evaluations, whereas stochastic gradient descent can reach (tightly) a simple regret in $O(1/N)$. It has been conjectured that gradient approximation by finite differences (hence, not a comparison-based method)"},"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":"1604.08459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-04-28T15:18:07Z","cross_cats_sorted":[],"title_canon_sha256":"ba5df6c0a94334aaaa34ef4f10e90d6a1d9b6135a79ad369cddd2494cec34791","abstract_canon_sha256":"092d69d495efb9bce60f64b40e843a6bd0c97016183ce74182c093121e0421bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:03.915906Z","signature_b64":"qV96fek8KtdIkgSRylTRM4SgkOG9m1Tg1pxZvIQuR7P+WChMJ53dJJuZdz4d7EC7+w/hCZxSgrlVoh1EZYlXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0f4e630e35d4f5072463123c8fb144a1fa7fc6acfe9adf9fa14c43c1d6e835a","last_reissued_at":"2026-05-18T01:16:03.915250Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:03.915250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noisy Optimization: Fast Convergence Rates with Comparison-Based Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"LRI, Marie-Liesse Cauwet (INRIA, Olivier Teytaud (LRI, TAO)","submitted_at":"2016-04-28T15:18:07Z","abstract_excerpt":"Derivative Free Optimization is known to be an efficient and robust method to tackle the black-box optimization problem. When it comes to noisy functions, classical comparison-based algorithms are slower than gradient-based algorithms. For quadratic functions, Evolutionary Algorithms without large mutations have a simple regret at best $O(1/ \\sqrt{N})$ when $N$ is the number of function evaluations, whereas stochastic gradient descent can reach (tightly) a simple regret in $O(1/N)$. It has been conjectured that gradient approximation by finite differences (hence, not a comparison-based method)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.08459","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":""},"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":"1604.08459","created_at":"2026-05-18T01:16:03.915353+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.08459v1","created_at":"2026-05-18T01:16:03.915353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.08459","created_at":"2026-05-18T01:16:03.915353+00:00"},{"alias_kind":"pith_short_12","alias_value":"YD2OMMHDLVHV","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"YD2OMMHDLVHVA4SG","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"YD2OMMHD","created_at":"2026-05-18T12:30:53.716459+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/YD2OMMHDLVHVA4SGGER4R6YUJI","json":"https://pith.science/pith/YD2OMMHDLVHVA4SGGER4R6YUJI.json","graph_json":"https://pith.science/api/pith-number/YD2OMMHDLVHVA4SGGER4R6YUJI/graph.json","events_json":"https://pith.science/api/pith-number/YD2OMMHDLVHVA4SGGER4R6YUJI/events.json","paper":"https://pith.science/paper/YD2OMMHD"},"agent_actions":{"view_html":"https://pith.science/pith/YD2OMMHDLVHVA4SGGER4R6YUJI","download_json":"https://pith.science/pith/YD2OMMHDLVHVA4SGGER4R6YUJI.json","view_paper":"https://pith.science/paper/YD2OMMHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.08459&json=true","fetch_graph":"https://pith.science/api/pith-number/YD2OMMHDLVHVA4SGGER4R6YUJI/graph.json","fetch_events":"https://pith.science/api/pith-number/YD2OMMHDLVHVA4SGGER4R6YUJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YD2OMMHDLVHVA4SGGER4R6YUJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YD2OMMHDLVHVA4SGGER4R6YUJI/action/storage_attestation","attest_author":"https://pith.science/pith/YD2OMMHDLVHVA4SGGER4R6YUJI/action/author_attestation","sign_citation":"https://pith.science/pith/YD2OMMHDLVHVA4SGGER4R6YUJI/action/citation_signature","submit_replication":"https://pith.science/pith/YD2OMMHDLVHVA4SGGER4R6YUJI/action/replication_record"}},"created_at":"2026-05-18T01:16:03.915353+00:00","updated_at":"2026-05-18T01:16:03.915353+00:00"}