{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MEJ4XNFCER5CGOGGHS77BBQJMH","short_pith_number":"pith:MEJ4XNFC","schema_version":"1.0","canonical_sha256":"6113cbb4a2247a2338c63cbff0860961d5c3af1d40ae17d5aaf4c8693ca65d5a","source":{"kind":"arxiv","id":"1802.08941","version":1},"attestation_state":"computed","paper":{"title":"Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solutions for Nonconvex Distributed Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"math.OC","authors_text":"Jason D. Lee, Meisam Razaviyayn, Mingyi Hong","submitted_at":"2018-02-25T01:59:05Z","abstract_excerpt":"In this work, we study two first-order primal-dual based algorithms, the Gradient Primal-Dual Algorithm (GPDA) and the Gradient Alternating Direction Method of Multipliers (GADMM), for solving a class of linearly constrained non-convex optimization problems. We show that with random initialization of the primal and dual variables, both algorithms are able to compute second-order stationary solutions (ss2) with probability one. This is the first result showing that primal-dual algorithm is capable of finding ss2 when only using first-order information, it also extends the existing results for f"},"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":"1802.08941","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-25T01:59:05Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"8362feaef563bc0ffcaefa6e53cfda495e1ceec6be8f72bbe2f54bae203b303e","abstract_canon_sha256":"a377aae2b922c089994e212c7bec8d44ad3ca2d862a46e46f0b2b84366a454e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:35.986031Z","signature_b64":"mkBfiDcDof3LPdx71m8zU7+ZmvhXtzba+OIGwM1YmPiA24Y+I+Ge0sga2A26ndfJM5oJlg/88jc/SEWuecUCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6113cbb4a2247a2338c63cbff0860961d5c3af1d40ae17d5aaf4c8693ca65d5a","last_reissued_at":"2026-05-18T00:22:35.985371Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:35.985371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solutions for Nonconvex Distributed Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"math.OC","authors_text":"Jason D. Lee, Meisam Razaviyayn, Mingyi Hong","submitted_at":"2018-02-25T01:59:05Z","abstract_excerpt":"In this work, we study two first-order primal-dual based algorithms, the Gradient Primal-Dual Algorithm (GPDA) and the Gradient Alternating Direction Method of Multipliers (GADMM), for solving a class of linearly constrained non-convex optimization problems. We show that with random initialization of the primal and dual variables, both algorithms are able to compute second-order stationary solutions (ss2) with probability one. This is the first result showing that primal-dual algorithm is capable of finding ss2 when only using first-order information, it also extends the existing results for f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08941","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":""},"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":"1802.08941","created_at":"2026-05-18T00:22:35.985454+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.08941v1","created_at":"2026-05-18T00:22:35.985454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08941","created_at":"2026-05-18T00:22:35.985454+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEJ4XNFCER5C","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEJ4XNFCER5CGOGG","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEJ4XNFC","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEJ4XNFCER5CGOGGHS77BBQJMH","json":"https://pith.science/pith/MEJ4XNFCER5CGOGGHS77BBQJMH.json","graph_json":"https://pith.science/api/pith-number/MEJ4XNFCER5CGOGGHS77BBQJMH/graph.json","events_json":"https://pith.science/api/pith-number/MEJ4XNFCER5CGOGGHS77BBQJMH/events.json","paper":"https://pith.science/paper/MEJ4XNFC"},"agent_actions":{"view_html":"https://pith.science/pith/MEJ4XNFCER5CGOGGHS77BBQJMH","download_json":"https://pith.science/pith/MEJ4XNFCER5CGOGGHS77BBQJMH.json","view_paper":"https://pith.science/paper/MEJ4XNFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.08941&json=true","fetch_graph":"https://pith.science/api/pith-number/MEJ4XNFCER5CGOGGHS77BBQJMH/graph.json","fetch_events":"https://pith.science/api/pith-number/MEJ4XNFCER5CGOGGHS77BBQJMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEJ4XNFCER5CGOGGHS77BBQJMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEJ4XNFCER5CGOGGHS77BBQJMH/action/storage_attestation","attest_author":"https://pith.science/pith/MEJ4XNFCER5CGOGGHS77BBQJMH/action/author_attestation","sign_citation":"https://pith.science/pith/MEJ4XNFCER5CGOGGHS77BBQJMH/action/citation_signature","submit_replication":"https://pith.science/pith/MEJ4XNFCER5CGOGGHS77BBQJMH/action/replication_record"}},"created_at":"2026-05-18T00:22:35.985454+00:00","updated_at":"2026-05-18T00:22:35.985454+00:00"}