{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QUVOKIP7QX262X2GBJ3P7BYNSS","short_pith_number":"pith:QUVOKIP7","schema_version":"1.0","canonical_sha256":"852ae521ff85f5ed5f460a76ff870d94982305bf9928bc794bbf35036944e47d","source":{"kind":"arxiv","id":"2307.04504","version":3},"attestation_state":"computed","paper":{"title":"An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Guy Kornowski, Ohad Shamir","submitted_at":"2023-07-10T11:56:04Z","abstract_excerpt":"We study the complexity of producing $(\\delta,\\epsilon)$-stationary points of Lipschitz objectives which are possibly neither smooth nor convex, using only noisy function evaluations. Recent works proposed several stochastic zero-order algorithms that solve this task, all of which suffer from a dimension-dependence of $\\Omega(d^{3/2})$ where $d$ is the dimension of the problem, which was conjectured to be optimal. We refute this conjecture by providing a faster algorithm that has complexity $O(d\\delta^{-1}\\epsilon^{-3})$, which is optimal (up to numerical constants) with respect to $d$ and als"},"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":"2307.04504","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-10T11:56:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8e85f5e37235e9b3ed314c60c944be0c38be7f759a85e976dea29f1abf978f40","abstract_canon_sha256":"7b4eb6ef08e1e9d423351bc7875a7ed5d754fb7964187a4e15774e2d79850d78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:57.190739Z","signature_b64":"UUtmh6O/4TSSaIU61qa6tiDvzQgyCi1x6vHWX5q5QjkVjQTeLfFWUQuWHZCwZmJgNV6TlUN/eS4B8m+hnP+SAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"852ae521ff85f5ed5f460a76ff870d94982305bf9928bc794bbf35036944e47d","last_reissued_at":"2026-07-05T08:07:57.190305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:57.190305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Guy Kornowski, Ohad Shamir","submitted_at":"2023-07-10T11:56:04Z","abstract_excerpt":"We study the complexity of producing $(\\delta,\\epsilon)$-stationary points of Lipschitz objectives which are possibly neither smooth nor convex, using only noisy function evaluations. Recent works proposed several stochastic zero-order algorithms that solve this task, all of which suffer from a dimension-dependence of $\\Omega(d^{3/2})$ where $d$ is the dimension of the problem, which was conjectured to be optimal. We refute this conjecture by providing a faster algorithm that has complexity $O(d\\delta^{-1}\\epsilon^{-3})$, which is optimal (up to numerical constants) with respect to $d$ and als"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04504","kind":"arxiv","version":3},"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/2307.04504/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":"2307.04504","created_at":"2026-07-05T08:07:57.190364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.04504v3","created_at":"2026-07-05T08:07:57.190364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04504","created_at":"2026-07-05T08:07:57.190364+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUVOKIP7QX26","created_at":"2026-07-05T08:07:57.190364+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUVOKIP7QX262X2G","created_at":"2026-07-05T08:07:57.190364+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUVOKIP7","created_at":"2026-07-05T08:07:57.190364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.13496","citing_title":"Revisiting Randomized Smoothing: Nonsmooth Nonconvex Optimization Beyond Global Lipschitz Continuity","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QUVOKIP7QX262X2GBJ3P7BYNSS","json":"https://pith.science/pith/QUVOKIP7QX262X2GBJ3P7BYNSS.json","graph_json":"https://pith.science/api/pith-number/QUVOKIP7QX262X2GBJ3P7BYNSS/graph.json","events_json":"https://pith.science/api/pith-number/QUVOKIP7QX262X2GBJ3P7BYNSS/events.json","paper":"https://pith.science/paper/QUVOKIP7"},"agent_actions":{"view_html":"https://pith.science/pith/QUVOKIP7QX262X2GBJ3P7BYNSS","download_json":"https://pith.science/pith/QUVOKIP7QX262X2GBJ3P7BYNSS.json","view_paper":"https://pith.science/paper/QUVOKIP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.04504&json=true","fetch_graph":"https://pith.science/api/pith-number/QUVOKIP7QX262X2GBJ3P7BYNSS/graph.json","fetch_events":"https://pith.science/api/pith-number/QUVOKIP7QX262X2GBJ3P7BYNSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUVOKIP7QX262X2GBJ3P7BYNSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUVOKIP7QX262X2GBJ3P7BYNSS/action/storage_attestation","attest_author":"https://pith.science/pith/QUVOKIP7QX262X2GBJ3P7BYNSS/action/author_attestation","sign_citation":"https://pith.science/pith/QUVOKIP7QX262X2GBJ3P7BYNSS/action/citation_signature","submit_replication":"https://pith.science/pith/QUVOKIP7QX262X2GBJ3P7BYNSS/action/replication_record"}},"created_at":"2026-07-05T08:07:57.190364+00:00","updated_at":"2026-07-05T08:07:57.190364+00:00"}