{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6WY257G7LZUU5M6P7PLRIIUNJG","short_pith_number":"pith:6WY257G7","schema_version":"1.0","canonical_sha256":"f5b1aefcdf5e694eb3cffbd714228d498c9a624e5613960eb10484600cd83f1f","source":{"kind":"arxiv","id":"2502.05600","version":2},"attestation_state":"computed","paper":{"title":"A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Kunjie Ren, Luo Luo","submitted_at":"2025-02-08T15:02:51Z","abstract_excerpt":"This paper considers zeroth-order optimization for stochastic convex minimization problem. We propose a parameter-free stochastic zeroth-order method (POEM) by introducing a step-size scheme based on the distance over finite difference and an adaptive smoothing parameter. We provide the theoretical analysis to show that POEM achieves the near-optimal stochastic zeroth-order oracle complexity. We further conduct the numerical experiments to demonstrate POEM outperforms existing zeroth-order methods in practice."},"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":"2502.05600","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-08T15:02:51Z","cross_cats_sorted":[],"title_canon_sha256":"50225dbed4a4c5f46ddf5f91fd85021772b00afde2e93d547aacc9260df204c1","abstract_canon_sha256":"64591e8a9354f92f44d718f2e1ad2321f898452652570594ba70df9c20144ffb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:23.152869Z","signature_b64":"mVAX9RagZmylmLFh+NZNt4kfWvxZx5jjDz4CoI6QfFUiAp3Lu1twyqiRSbDcx22HhR/n/q89+qEnzt+9LPo5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5b1aefcdf5e694eb3cffbd714228d498c9a624e5613960eb10484600cd83f1f","last_reissued_at":"2026-07-05T10:58:23.152306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:23.152306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Kunjie Ren, Luo Luo","submitted_at":"2025-02-08T15:02:51Z","abstract_excerpt":"This paper considers zeroth-order optimization for stochastic convex minimization problem. We propose a parameter-free stochastic zeroth-order method (POEM) by introducing a step-size scheme based on the distance over finite difference and an adaptive smoothing parameter. We provide the theoretical analysis to show that POEM achieves the near-optimal stochastic zeroth-order oracle complexity. We further conduct the numerical experiments to demonstrate POEM outperforms existing zeroth-order methods in practice."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05600","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.05600/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":"2502.05600","created_at":"2026-07-05T10:58:23.152380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05600v2","created_at":"2026-07-05T10:58:23.152380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05600","created_at":"2026-07-05T10:58:23.152380+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WY257G7LZUU","created_at":"2026-07-05T10:58:23.152380+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WY257G7LZUU5M6P","created_at":"2026-07-05T10:58:23.152380+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WY257G7","created_at":"2026-07-05T10:58:23.152380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.14970","citing_title":"Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WY257G7LZUU5M6P7PLRIIUNJG","json":"https://pith.science/pith/6WY257G7LZUU5M6P7PLRIIUNJG.json","graph_json":"https://pith.science/api/pith-number/6WY257G7LZUU5M6P7PLRIIUNJG/graph.json","events_json":"https://pith.science/api/pith-number/6WY257G7LZUU5M6P7PLRIIUNJG/events.json","paper":"https://pith.science/paper/6WY257G7"},"agent_actions":{"view_html":"https://pith.science/pith/6WY257G7LZUU5M6P7PLRIIUNJG","download_json":"https://pith.science/pith/6WY257G7LZUU5M6P7PLRIIUNJG.json","view_paper":"https://pith.science/paper/6WY257G7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05600&json=true","fetch_graph":"https://pith.science/api/pith-number/6WY257G7LZUU5M6P7PLRIIUNJG/graph.json","fetch_events":"https://pith.science/api/pith-number/6WY257G7LZUU5M6P7PLRIIUNJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WY257G7LZUU5M6P7PLRIIUNJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WY257G7LZUU5M6P7PLRIIUNJG/action/storage_attestation","attest_author":"https://pith.science/pith/6WY257G7LZUU5M6P7PLRIIUNJG/action/author_attestation","sign_citation":"https://pith.science/pith/6WY257G7LZUU5M6P7PLRIIUNJG/action/citation_signature","submit_replication":"https://pith.science/pith/6WY257G7LZUU5M6P7PLRIIUNJG/action/replication_record"}},"created_at":"2026-07-05T10:58:23.152380+00:00","updated_at":"2026-07-05T10:58:23.152380+00:00"}