{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6W677DEXVIOJZKOKR7QYVUGPSB","short_pith_number":"pith:6W677DEX","schema_version":"1.0","canonical_sha256":"f5bdff8c97aa1c9ca9ca8fe18ad0cf904b790d69c60f5deeb428665a17928ded","source":{"kind":"arxiv","id":"2207.06304","version":3},"attestation_state":"computed","paper":{"title":"On the Iteration Complexity of Smoothed Proximal ALM for Nonconvex Optimization Problem with Convex Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Jiawei Zhang, Wenqiang Pu, Zhi-Quan Luo","submitted_at":"2022-07-13T15:57:52Z","abstract_excerpt":"It is well-known that the lower bound of iteration complexity for solving nonconvex unconstrained optimization problems is $\\Omega(1/\\epsilon^2)$, which can be achieved by standard gradient descent algorithm when the objective function is smooth. This lower bound still holds for nonconvex constrained problems, while it is still unknown whether a first-order method can achieve this lower bound. In this paper, we show that a simple single-loop first-order algorithm called smoothed proximal augmented Lagrangian method (ALM) can achieve such iteration complexity lower bound. The key technical cont"},"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":"2207.06304","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-07-13T15:57:52Z","cross_cats_sorted":[],"title_canon_sha256":"91796275b61aeb2ce07e89e6affbc0cdc865095c109100f2e4655982022a6095","abstract_canon_sha256":"389758633f856c26253723d31064c69dd522f3590324ed27d94c4e0394f87512"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:13.781464Z","signature_b64":"96ad8K5j6K/GKyxa3mx/GIm0TaFmGDxH30mKJw5Y62c2NmSBEpRW1mC2oJtGon8ZMgGsrq6hw4LStuEJmIztAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5bdff8c97aa1c9ca9ca8fe18ad0cf904b790d69c60f5deeb428665a17928ded","last_reissued_at":"2026-07-05T05:12:13.781013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:13.781013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Iteration Complexity of Smoothed Proximal ALM for Nonconvex Optimization Problem with Convex Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Jiawei Zhang, Wenqiang Pu, Zhi-Quan Luo","submitted_at":"2022-07-13T15:57:52Z","abstract_excerpt":"It is well-known that the lower bound of iteration complexity for solving nonconvex unconstrained optimization problems is $\\Omega(1/\\epsilon^2)$, which can be achieved by standard gradient descent algorithm when the objective function is smooth. This lower bound still holds for nonconvex constrained problems, while it is still unknown whether a first-order method can achieve this lower bound. In this paper, we show that a simple single-loop first-order algorithm called smoothed proximal augmented Lagrangian method (ALM) can achieve such iteration complexity lower bound. The key technical cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06304","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/2207.06304/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":"2207.06304","created_at":"2026-07-05T05:12:13.781105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.06304v3","created_at":"2026-07-05T05:12:13.781105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06304","created_at":"2026-07-05T05:12:13.781105+00:00"},{"alias_kind":"pith_short_12","alias_value":"6W677DEXVIOJ","created_at":"2026-07-05T05:12:13.781105+00:00"},{"alias_kind":"pith_short_16","alias_value":"6W677DEXVIOJZKOK","created_at":"2026-07-05T05:12:13.781105+00:00"},{"alias_kind":"pith_short_8","alias_value":"6W677DEX","created_at":"2026-07-05T05:12:13.781105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18618","citing_title":"Stochastic Penalty-Barrier Methods for Constrained Machine Learning","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6W677DEXVIOJZKOKR7QYVUGPSB","json":"https://pith.science/pith/6W677DEXVIOJZKOKR7QYVUGPSB.json","graph_json":"https://pith.science/api/pith-number/6W677DEXVIOJZKOKR7QYVUGPSB/graph.json","events_json":"https://pith.science/api/pith-number/6W677DEXVIOJZKOKR7QYVUGPSB/events.json","paper":"https://pith.science/paper/6W677DEX"},"agent_actions":{"view_html":"https://pith.science/pith/6W677DEXVIOJZKOKR7QYVUGPSB","download_json":"https://pith.science/pith/6W677DEXVIOJZKOKR7QYVUGPSB.json","view_paper":"https://pith.science/paper/6W677DEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.06304&json=true","fetch_graph":"https://pith.science/api/pith-number/6W677DEXVIOJZKOKR7QYVUGPSB/graph.json","fetch_events":"https://pith.science/api/pith-number/6W677DEXVIOJZKOKR7QYVUGPSB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6W677DEXVIOJZKOKR7QYVUGPSB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6W677DEXVIOJZKOKR7QYVUGPSB/action/storage_attestation","attest_author":"https://pith.science/pith/6W677DEXVIOJZKOKR7QYVUGPSB/action/author_attestation","sign_citation":"https://pith.science/pith/6W677DEXVIOJZKOKR7QYVUGPSB/action/citation_signature","submit_replication":"https://pith.science/pith/6W677DEXVIOJZKOKR7QYVUGPSB/action/replication_record"}},"created_at":"2026-07-05T05:12:13.781105+00:00","updated_at":"2026-07-05T05:12:13.781105+00:00"}