{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UTPQOW464IHZD2FEV66ZGGRG2B","short_pith_number":"pith:UTPQOW46","schema_version":"1.0","canonical_sha256":"a4df075b9ee20f91e8a4afbd931a26d0642f576c8446838ce7cf3a7859a89893","source":{"kind":"arxiv","id":"2310.18883","version":1},"attestation_state":"computed","paper":{"title":"A Zeroth-Order Variance-Reduced Method for Decentralized Stochastic Non-convex Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hongxu Chen, Jinchi Chen, Ke Wei","submitted_at":"2023-10-29T03:13:45Z","abstract_excerpt":"In this paper, we consider a distributed stochastic non-convex optimization problem, which is about minimizing a sum of $n$ local cost functions over a network with only zeroth-order information. A novel single-loop Decentralized Zeroth-Order Variance Reduction algorithm, called DZOVR, is proposed, which combines two-point gradient estimation, momentum-based variance reduction technique, and gradient tracking. Under mild assumptions, we show that the algorithm is able to achieve $\\mathcal{O}(dn^{-1}\\epsilon^{-3})$ sampling complexity at each node to reach an $\\epsilon$-accurate stationary poin"},"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":"2310.18883","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-10-29T03:13:45Z","cross_cats_sorted":[],"title_canon_sha256":"327009eb36f7974f95cc5fb049374a2be1bab46c6b2edd97ecafbeaca6a9f52d","abstract_canon_sha256":"080b8d52d5761a36e7e691a4ce3a3108eead28ec6c00415a84f25e0f979795c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:42.845613Z","signature_b64":"aC/zurB+Go+laXdEFn2Tau1G4kEb6vBqZsfpKLm1t0mdaNfvylDtHcrj19hdLPvRbBSibcDQdrJQuMcDKGH+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4df075b9ee20f91e8a4afbd931a26d0642f576c8446838ce7cf3a7859a89893","last_reissued_at":"2026-07-05T07:06:42.845078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:42.845078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Zeroth-Order Variance-Reduced Method for Decentralized Stochastic Non-convex Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hongxu Chen, Jinchi Chen, Ke Wei","submitted_at":"2023-10-29T03:13:45Z","abstract_excerpt":"In this paper, we consider a distributed stochastic non-convex optimization problem, which is about minimizing a sum of $n$ local cost functions over a network with only zeroth-order information. A novel single-loop Decentralized Zeroth-Order Variance Reduction algorithm, called DZOVR, is proposed, which combines two-point gradient estimation, momentum-based variance reduction technique, and gradient tracking. Under mild assumptions, we show that the algorithm is able to achieve $\\mathcal{O}(dn^{-1}\\epsilon^{-3})$ sampling complexity at each node to reach an $\\epsilon$-accurate stationary poin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18883","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.18883/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":"2310.18883","created_at":"2026-07-05T07:06:42.845131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18883v1","created_at":"2026-07-05T07:06:42.845131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18883","created_at":"2026-07-05T07:06:42.845131+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTPQOW464IHZ","created_at":"2026-07-05T07:06:42.845131+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTPQOW464IHZD2FE","created_at":"2026-07-05T07:06:42.845131+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTPQOW46","created_at":"2026-07-05T07:06:42.845131+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21833","citing_title":"Memory Savings at What Cost? A Study of Alternatives to Backpropagation","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UTPQOW464IHZD2FEV66ZGGRG2B","json":"https://pith.science/pith/UTPQOW464IHZD2FEV66ZGGRG2B.json","graph_json":"https://pith.science/api/pith-number/UTPQOW464IHZD2FEV66ZGGRG2B/graph.json","events_json":"https://pith.science/api/pith-number/UTPQOW464IHZD2FEV66ZGGRG2B/events.json","paper":"https://pith.science/paper/UTPQOW46"},"agent_actions":{"view_html":"https://pith.science/pith/UTPQOW464IHZD2FEV66ZGGRG2B","download_json":"https://pith.science/pith/UTPQOW464IHZD2FEV66ZGGRG2B.json","view_paper":"https://pith.science/paper/UTPQOW46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18883&json=true","fetch_graph":"https://pith.science/api/pith-number/UTPQOW464IHZD2FEV66ZGGRG2B/graph.json","fetch_events":"https://pith.science/api/pith-number/UTPQOW464IHZD2FEV66ZGGRG2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTPQOW464IHZD2FEV66ZGGRG2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTPQOW464IHZD2FEV66ZGGRG2B/action/storage_attestation","attest_author":"https://pith.science/pith/UTPQOW464IHZD2FEV66ZGGRG2B/action/author_attestation","sign_citation":"https://pith.science/pith/UTPQOW464IHZD2FEV66ZGGRG2B/action/citation_signature","submit_replication":"https://pith.science/pith/UTPQOW464IHZD2FEV66ZGGRG2B/action/replication_record"}},"created_at":"2026-07-05T07:06:42.845131+00:00","updated_at":"2026-07-05T07:06:42.845131+00:00"}