{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SKZS5JELQC6VH3OYMHNP3IUSVG","short_pith_number":"pith:SKZS5JEL","schema_version":"1.0","canonical_sha256":"92b32ea48b80bd53edd861dafda292a9963f7b86d89695d323e7e5face25154c","source":{"kind":"arxiv","id":"2504.08223","version":2},"attestation_state":"computed","paper":{"title":"Stochastic momentum ADMM for nonconvex and nonsmooth optimization with application to PnP algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Boyu Wang, Hongxia Wang, Jiachen Jin, Juan Zhou, Kangkang Deng, Shuchang Zhang","submitted_at":"2025-04-11T03:11:51Z","abstract_excerpt":"This paper proposes SMADMM, a single-loop Stochastic Momentum Alternating Direction Method of Multipliers for solving a class of nonconvex and nonsmooth composite optimization problems. SMADMM achieves the optimal oracle complexity of $\\mathcal{O}(\\epsilon^{-3/2})$ in the online setting. Unlike previous stochastic ADMM algorithms that require large mini-batches or a double-loop structure, SMADMM uses only $\\mathcal{O}(1)$ stochastic gradient evaluations per iteration and avoids costly restarts. To further improve practicality, we incorporate dynamic step sizes and penalty parameters, proving t"},"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":"2504.08223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-04-11T03:11:51Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"a6700b621e17c42acf775c48e944331f7e0efc37e14ba76e013157bacb522246","abstract_canon_sha256":"fd5f6f863f5b97d57f2e696bb1610215de843be046b761ce826b619376bafdab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:36.300294Z","signature_b64":"jrLrC6vLK2fVa+hSYltBqcADMp1JsmhgWsbcCeijo0jXTd2tDAf/OqM3ULhRE87R192pG2y+1up5I6oX+6f6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92b32ea48b80bd53edd861dafda292a9963f7b86d89695d323e7e5face25154c","last_reissued_at":"2026-07-05T10:51:36.299765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:36.299765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic momentum ADMM for nonconvex and nonsmooth optimization with application to PnP algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Boyu Wang, Hongxia Wang, Jiachen Jin, Juan Zhou, Kangkang Deng, Shuchang Zhang","submitted_at":"2025-04-11T03:11:51Z","abstract_excerpt":"This paper proposes SMADMM, a single-loop Stochastic Momentum Alternating Direction Method of Multipliers for solving a class of nonconvex and nonsmooth composite optimization problems. SMADMM achieves the optimal oracle complexity of $\\mathcal{O}(\\epsilon^{-3/2})$ in the online setting. Unlike previous stochastic ADMM algorithms that require large mini-batches or a double-loop structure, SMADMM uses only $\\mathcal{O}(1)$ stochastic gradient evaluations per iteration and avoids costly restarts. To further improve practicality, we incorporate dynamic step sizes and penalty parameters, proving t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08223","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/2504.08223/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":"2504.08223","created_at":"2026-07-05T10:51:36.299843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08223v2","created_at":"2026-07-05T10:51:36.299843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08223","created_at":"2026-07-05T10:51:36.299843+00:00"},{"alias_kind":"pith_short_12","alias_value":"SKZS5JELQC6V","created_at":"2026-07-05T10:51:36.299843+00:00"},{"alias_kind":"pith_short_16","alias_value":"SKZS5JELQC6VH3OY","created_at":"2026-07-05T10:51:36.299843+00:00"},{"alias_kind":"pith_short_8","alias_value":"SKZS5JEL","created_at":"2026-07-05T10:51:36.299843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.09485","citing_title":"Single-loop $\\mathcal{O}(\\epsilon^{-3})$ stochastic smoothing algorithms for nonsmooth Riemannian optimization","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SKZS5JELQC6VH3OYMHNP3IUSVG","json":"https://pith.science/pith/SKZS5JELQC6VH3OYMHNP3IUSVG.json","graph_json":"https://pith.science/api/pith-number/SKZS5JELQC6VH3OYMHNP3IUSVG/graph.json","events_json":"https://pith.science/api/pith-number/SKZS5JELQC6VH3OYMHNP3IUSVG/events.json","paper":"https://pith.science/paper/SKZS5JEL"},"agent_actions":{"view_html":"https://pith.science/pith/SKZS5JELQC6VH3OYMHNP3IUSVG","download_json":"https://pith.science/pith/SKZS5JELQC6VH3OYMHNP3IUSVG.json","view_paper":"https://pith.science/paper/SKZS5JEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08223&json=true","fetch_graph":"https://pith.science/api/pith-number/SKZS5JELQC6VH3OYMHNP3IUSVG/graph.json","fetch_events":"https://pith.science/api/pith-number/SKZS5JELQC6VH3OYMHNP3IUSVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SKZS5JELQC6VH3OYMHNP3IUSVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SKZS5JELQC6VH3OYMHNP3IUSVG/action/storage_attestation","attest_author":"https://pith.science/pith/SKZS5JELQC6VH3OYMHNP3IUSVG/action/author_attestation","sign_citation":"https://pith.science/pith/SKZS5JELQC6VH3OYMHNP3IUSVG/action/citation_signature","submit_replication":"https://pith.science/pith/SKZS5JELQC6VH3OYMHNP3IUSVG/action/replication_record"}},"created_at":"2026-07-05T10:51:36.299843+00:00","updated_at":"2026-07-05T10:51:36.299843+00:00"}