{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LBCTHNMWBXB5VJYAICKRKRCW7X","short_pith_number":"pith:LBCTHNMW","schema_version":"1.0","canonical_sha256":"584533b5960dc3daa7004095154456fdd6a3beb511caaae809365cd3ba2cc06e","source":{"kind":"arxiv","id":"2604.23613","version":2},"attestation_state":"computed","paper":{"title":"High-Probability Guarantees for Random Zeroth-Order (Stochastic) Gradient Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Random zeroth-order gradient descent reaches ε-suboptimality with probability 1-δ using O((dL/μ)log(1/ε) + log(1/δ)) queries for smooth strongly convex functions.","cross_cats":[],"primary_cat":"math.OC","authors_text":"Haishan Ye","submitted_at":"2026-04-26T09:02:05Z","abstract_excerpt":"Zeroth-order optimization aims to minimize an objective function using only function evaluations, and is therefore fundamental in black-box optimization, hyperparameter tuning, bandit learning, and adversarial machine learning. While classical zeroth-order methods are well understood in expectation, much less is known about their high-probability behavior, especially for smooth and strongly convex objectives. In this paper, we establish high-probability convergence guarantees for random zeroth-order gradient descent in both deterministic and stochastic settings. For deterministic $L$-smooth an"},"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":"2604.23613","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-04-26T09:02:05Z","cross_cats_sorted":[],"title_canon_sha256":"fb12827e561a73ae399edcf4385c842f39c37504b26d324ca326e193033a4e26","abstract_canon_sha256":"5ad99d955f16be0532727a4cadd9afc4650979d555d149230f3e91e7b9c8e0d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:07.537770Z","signature_b64":"JlOdVvfp5BmJteg+yOE+VOQFj/CvwxO5u4r6Aprg0B/PZl5yPdZd13lRSHdr3/spE49ZK7X6I3iJZ8pinRH4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"584533b5960dc3daa7004095154456fdd6a3beb511caaae809365cd3ba2cc06e","last_reissued_at":"2026-06-23T01:12:07.537231Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:07.537231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Probability Guarantees for Random Zeroth-Order (Stochastic) Gradient Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Random zeroth-order gradient descent reaches ε-suboptimality with probability 1-δ using O((dL/μ)log(1/ε) + log(1/δ)) queries for smooth strongly convex functions.","cross_cats":[],"primary_cat":"math.OC","authors_text":"Haishan Ye","submitted_at":"2026-04-26T09:02:05Z","abstract_excerpt":"Zeroth-order optimization aims to minimize an objective function using only function evaluations, and is therefore fundamental in black-box optimization, hyperparameter tuning, bandit learning, and adversarial machine learning. While classical zeroth-order methods are well understood in expectation, much less is known about their high-probability behavior, especially for smooth and strongly convex objectives. In this paper, we establish high-probability convergence guarantees for random zeroth-order gradient descent in both deterministic and stochastic settings. For deterministic $L$-smooth an"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"For deterministic L-smooth and μ-strongly convex objectives of d-dimension, the classical two-query random zeroth-order method finds an ε-suboptimal solution with probability at least 1-δ using O((dL/μ)log(1/ε) + log(1/δ)) function queries. For stochastic objectives under bounded-noise, random zeroth-order SGD achieves the same with O(d log(1/ε)(log(1/ε)+log(1/δ))/ε) queries.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The objective is L-smooth and μ-strongly convex (deterministic case) or has bounded noise without uniformly bounded stochastic gradients (stochastic case); these are invoked to derive the stated query complexities but their necessity for the high-probability result is not relaxed in the abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Random zeroth-order gradient descent reaches ε-suboptimal solutions with probability 1-δ using O((dL/μ)log(1/ε) + log(1/δ)) queries deterministically and O(d log(1/ε)(log(1/ε)+log(1/δ))/ε) queries under bounded stochastic noise.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Random zeroth-order gradient descent reaches ε-suboptimality with probability 1-δ using O((dL/μ)log(1/ε) + log(1/δ)) queries for smooth strongly convex functions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5bb2a04d37b030016610e3ec1b6423c3fa7afedf47d8d7ea0fe9bbba2e123b05"},"source":{"id":"2604.23613","kind":"arxiv","version":2},"verdict":{"id":"7b712e9e-3fec-4f67-8f27-f20344d87c54","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T05:45:08.341843Z","strongest_claim":"For deterministic L-smooth and μ-strongly convex objectives of d-dimension, the classical two-query random zeroth-order method finds an ε-suboptimal solution with probability at least 1-δ using O((dL/μ)log(1/ε) + log(1/δ)) function queries. For stochastic objectives under bounded-noise, random zeroth-order SGD achieves the same with O(d log(1/ε)(log(1/ε)+log(1/δ))/ε) queries.","one_line_summary":"Random zeroth-order gradient descent reaches ε-suboptimal solutions with probability 1-δ using O((dL/μ)log(1/ε) + log(1/δ)) queries deterministically and O(d log(1/ε)(log(1/ε)+log(1/δ))/ε) queries under bounded stochastic noise.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The objective is L-smooth and μ-strongly convex (deterministic case) or has bounded noise without uniformly bounded stochastic gradients (stochastic case); these are invoked to derive the stated query complexities but their necessity for the high-probability result is not relaxed in the abstract.","pith_extraction_headline":"Random zeroth-order gradient descent reaches ε-suboptimality with probability 1-δ using O((dL/μ)log(1/ε) + log(1/δ)) queries for smooth strongly convex functions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.23613/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T08:37:52.229328Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:56:21.762503Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"bc245d88e81ed969ac84eb025b90b20c273f3798bcd1040e7d6522cb2e1e25a5"},"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":"2604.23613","created_at":"2026-06-23T01:12:07.537298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.23613v2","created_at":"2026-06-23T01:12:07.537298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.23613","created_at":"2026-06-23T01:12:07.537298+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBCTHNMWBXB5","created_at":"2026-06-23T01:12:07.537298+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBCTHNMWBXB5VJYA","created_at":"2026-06-23T01:12:07.537298+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBCTHNMW","created_at":"2026-06-23T01:12:07.537298+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/LBCTHNMWBXB5VJYAICKRKRCW7X","json":"https://pith.science/pith/LBCTHNMWBXB5VJYAICKRKRCW7X.json","graph_json":"https://pith.science/api/pith-number/LBCTHNMWBXB5VJYAICKRKRCW7X/graph.json","events_json":"https://pith.science/api/pith-number/LBCTHNMWBXB5VJYAICKRKRCW7X/events.json","paper":"https://pith.science/paper/LBCTHNMW"},"agent_actions":{"view_html":"https://pith.science/pith/LBCTHNMWBXB5VJYAICKRKRCW7X","download_json":"https://pith.science/pith/LBCTHNMWBXB5VJYAICKRKRCW7X.json","view_paper":"https://pith.science/paper/LBCTHNMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.23613&json=true","fetch_graph":"https://pith.science/api/pith-number/LBCTHNMWBXB5VJYAICKRKRCW7X/graph.json","fetch_events":"https://pith.science/api/pith-number/LBCTHNMWBXB5VJYAICKRKRCW7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBCTHNMWBXB5VJYAICKRKRCW7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBCTHNMWBXB5VJYAICKRKRCW7X/action/storage_attestation","attest_author":"https://pith.science/pith/LBCTHNMWBXB5VJYAICKRKRCW7X/action/author_attestation","sign_citation":"https://pith.science/pith/LBCTHNMWBXB5VJYAICKRKRCW7X/action/citation_signature","submit_replication":"https://pith.science/pith/LBCTHNMWBXB5VJYAICKRKRCW7X/action/replication_record"}},"created_at":"2026-06-23T01:12:07.537298+00:00","updated_at":"2026-06-23T01:12:07.537298+00:00"}