{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4EOYGPJZEVZLF6QTYS26QMGQ27","short_pith_number":"pith:4EOYGPJZ","schema_version":"1.0","canonical_sha256":"e11d833d392572b2fa13c4b5e830d0d7da0973899c462dee9cce14d8e853f366","source":{"kind":"arxiv","id":"2406.14371","version":2},"attestation_state":"computed","paper":{"title":"AGDA+: Proximal Alternating Gradient Descent Ascent Method with a Nonmonotone Adaptive Step-Size Search for Nonconvex Minimax Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Necdet Serhat Aybat, Qiushui Xu, Xuan Zhang","submitted_at":"2024-06-20T14:42:16Z","abstract_excerpt":"We consider double-regularized nonconvex-strongly concave (NCSC) minimax problems of the form $(P):\\min_{x\\in\\mathcal{X}} \\max_{y\\in\\mathcal{Y}}g(x)+f(x,y)-h(y)$, where $g$, $h$ are closed convex, $f$ is $L$-smooth in $(x,y)$ and strongly concave in $y$. We propose a proximal alternating gradient descent ascent method AGDA+ that can adaptively choose nonmonotone primal-dual stepsizes to compute an approximate stationary point for $(P)$ without requiring the knowledge of the global Lipschitz constant $L$ and the concavity modulus $\\mu$. Using a nonmonotone step-size search (backtracking) scheme"},"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":"2406.14371","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-06-20T14:42:16Z","cross_cats_sorted":[],"title_canon_sha256":"aa1a8164f63b75e82d62e2ac1a6f275a87cf29f2fc0d2639a7c9b08830f2ee89","abstract_canon_sha256":"aa81e5c18fe96f6d38473f91e41800785abe3dc2562c209e51791b6c49850589"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:41.567243Z","signature_b64":"usU2Fx8AfDM+byQbPlDss+h0D80TSPURzUiEPIQlhrtZrJo5pKwn3HTAyNcOP3gBIcAgAdqp3/YrJWPD5K8DAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e11d833d392572b2fa13c4b5e830d0d7da0973899c462dee9cce14d8e853f366","last_reissued_at":"2026-07-05T10:06:41.566845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:41.566845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AGDA+: Proximal Alternating Gradient Descent Ascent Method with a Nonmonotone Adaptive Step-Size Search for Nonconvex Minimax Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Necdet Serhat Aybat, Qiushui Xu, Xuan Zhang","submitted_at":"2024-06-20T14:42:16Z","abstract_excerpt":"We consider double-regularized nonconvex-strongly concave (NCSC) minimax problems of the form $(P):\\min_{x\\in\\mathcal{X}} \\max_{y\\in\\mathcal{Y}}g(x)+f(x,y)-h(y)$, where $g$, $h$ are closed convex, $f$ is $L$-smooth in $(x,y)$ and strongly concave in $y$. We propose a proximal alternating gradient descent ascent method AGDA+ that can adaptively choose nonmonotone primal-dual stepsizes to compute an approximate stationary point for $(P)$ without requiring the knowledge of the global Lipschitz constant $L$ and the concavity modulus $\\mu$. Using a nonmonotone step-size search (backtracking) scheme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14371","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/2406.14371/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":"2406.14371","created_at":"2026-07-05T10:06:41.566902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14371v2","created_at":"2026-07-05T10:06:41.566902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14371","created_at":"2026-07-05T10:06:41.566902+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EOYGPJZEVZL","created_at":"2026-07-05T10:06:41.566902+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EOYGPJZEVZLF6QT","created_at":"2026-07-05T10:06:41.566902+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EOYGPJZ","created_at":"2026-07-05T10:06:41.566902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01595","citing_title":"Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Model","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4EOYGPJZEVZLF6QTYS26QMGQ27","json":"https://pith.science/pith/4EOYGPJZEVZLF6QTYS26QMGQ27.json","graph_json":"https://pith.science/api/pith-number/4EOYGPJZEVZLF6QTYS26QMGQ27/graph.json","events_json":"https://pith.science/api/pith-number/4EOYGPJZEVZLF6QTYS26QMGQ27/events.json","paper":"https://pith.science/paper/4EOYGPJZ"},"agent_actions":{"view_html":"https://pith.science/pith/4EOYGPJZEVZLF6QTYS26QMGQ27","download_json":"https://pith.science/pith/4EOYGPJZEVZLF6QTYS26QMGQ27.json","view_paper":"https://pith.science/paper/4EOYGPJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14371&json=true","fetch_graph":"https://pith.science/api/pith-number/4EOYGPJZEVZLF6QTYS26QMGQ27/graph.json","fetch_events":"https://pith.science/api/pith-number/4EOYGPJZEVZLF6QTYS26QMGQ27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EOYGPJZEVZLF6QTYS26QMGQ27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EOYGPJZEVZLF6QTYS26QMGQ27/action/storage_attestation","attest_author":"https://pith.science/pith/4EOYGPJZEVZLF6QTYS26QMGQ27/action/author_attestation","sign_citation":"https://pith.science/pith/4EOYGPJZEVZLF6QTYS26QMGQ27/action/citation_signature","submit_replication":"https://pith.science/pith/4EOYGPJZEVZLF6QTYS26QMGQ27/action/replication_record"}},"created_at":"2026-07-05T10:06:41.566902+00:00","updated_at":"2026-07-05T10:06:41.566902+00:00"}