{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:REZ6FDUBJJCF3A37FQQJMF663U","short_pith_number":"pith:REZ6FDUB","schema_version":"1.0","canonical_sha256":"8933e28e814a445d837f2c209617dedd1532f55fd2c217de16653a114ede0b98","source":{"kind":"arxiv","id":"1312.2139","version":2},"attestation_state":"computed","paper":{"title":"Optimal rates for zero-order convex optimization: the power of two function evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"math.OC","authors_text":"Andre Wibisono, John C. Duchi, Martin J. Wainwright, Michael I. Jordan","submitted_at":"2013-12-07T20:24:14Z","abstract_excerpt":"We consider derivative-free algorithms for stochastic and non-stochastic convex optimization problems that use only function values rather than gradients. Focusing on non-asymptotic bounds on convergence rates, we show that if pairs of function values are available, algorithms for $d$-dimensional optimization that use gradient estimates based on random perturbations suffer a factor of at most $\\sqrt{d}$ in convergence rate over traditional stochastic gradient methods. We establish such results for both smooth and non-smooth cases, sharpening previous analyses that suggested a worse dimension d"},"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":"1312.2139","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2013-12-07T20:24:14Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"05620d720e9ee266edb372b45197590fb5a69a45253f74a7862822c741666567","abstract_canon_sha256":"4433f68e389fd6c81604329b79af7e1dab4a24740b98c43707635af3b6a6e7ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:49.756818Z","signature_b64":"pcjMniWXB4iauB4S4VXJ/JygxR/Qvmtv4FYQTN+bQ0kpSO2XuhTC9O8LLxw9U15FLkurKZq2j7VMKHgPbmcRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8933e28e814a445d837f2c209617dedd1532f55fd2c217de16653a114ede0b98","last_reissued_at":"2026-05-18T02:44:49.756437Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:49.756437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal rates for zero-order convex optimization: the power of two function evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"math.OC","authors_text":"Andre Wibisono, John C. Duchi, Martin J. Wainwright, Michael I. Jordan","submitted_at":"2013-12-07T20:24:14Z","abstract_excerpt":"We consider derivative-free algorithms for stochastic and non-stochastic convex optimization problems that use only function values rather than gradients. Focusing on non-asymptotic bounds on convergence rates, we show that if pairs of function values are available, algorithms for $d$-dimensional optimization that use gradient estimates based on random perturbations suffer a factor of at most $\\sqrt{d}$ in convergence rate over traditional stochastic gradient methods. We establish such results for both smooth and non-smooth cases, sharpening previous analyses that suggested a worse dimension d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1312.2139","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":""},"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":"1312.2139","created_at":"2026-05-18T02:44:49.756496+00:00"},{"alias_kind":"arxiv_version","alias_value":"1312.2139v2","created_at":"2026-05-18T02:44:49.756496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1312.2139","created_at":"2026-05-18T02:44:49.756496+00:00"},{"alias_kind":"pith_short_12","alias_value":"REZ6FDUBJJCF","created_at":"2026-05-18T12:27:57.521954+00:00"},{"alias_kind":"pith_short_16","alias_value":"REZ6FDUBJJCF3A37","created_at":"2026-05-18T12:27:57.521954+00:00"},{"alias_kind":"pith_short_8","alias_value":"REZ6FDUB","created_at":"2026-05-18T12:27:57.521954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/REZ6FDUBJJCF3A37FQQJMF663U","json":"https://pith.science/pith/REZ6FDUBJJCF3A37FQQJMF663U.json","graph_json":"https://pith.science/api/pith-number/REZ6FDUBJJCF3A37FQQJMF663U/graph.json","events_json":"https://pith.science/api/pith-number/REZ6FDUBJJCF3A37FQQJMF663U/events.json","paper":"https://pith.science/paper/REZ6FDUB"},"agent_actions":{"view_html":"https://pith.science/pith/REZ6FDUBJJCF3A37FQQJMF663U","download_json":"https://pith.science/pith/REZ6FDUBJJCF3A37FQQJMF663U.json","view_paper":"https://pith.science/paper/REZ6FDUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1312.2139&json=true","fetch_graph":"https://pith.science/api/pith-number/REZ6FDUBJJCF3A37FQQJMF663U/graph.json","fetch_events":"https://pith.science/api/pith-number/REZ6FDUBJJCF3A37FQQJMF663U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REZ6FDUBJJCF3A37FQQJMF663U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REZ6FDUBJJCF3A37FQQJMF663U/action/storage_attestation","attest_author":"https://pith.science/pith/REZ6FDUBJJCF3A37FQQJMF663U/action/author_attestation","sign_citation":"https://pith.science/pith/REZ6FDUBJJCF3A37FQQJMF663U/action/citation_signature","submit_replication":"https://pith.science/pith/REZ6FDUBJJCF3A37FQQJMF663U/action/replication_record"}},"created_at":"2026-05-18T02:44:49.756496+00:00","updated_at":"2026-05-18T02:44:49.756496+00:00"}