{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QZEQBCGYF6HQACV33PG3JHZDH3","short_pith_number":"pith:QZEQBCGY","schema_version":"1.0","canonical_sha256":"86490088d82f8f000abbdbcdb49f233ed94d5da7e3df2f7f3e5e65b74a6713ba","source":{"kind":"arxiv","id":"2102.04653","version":2},"attestation_state":"computed","paper":{"title":"Proximal Gradient Descent-Ascent: Variable Convergence under K{\\L} Geometry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Tengyu Xu, Yingbin Liang, Yi Zhou, Ziyi Chen","submitted_at":"2021-02-09T05:35:53Z","abstract_excerpt":"The gradient descent-ascent (GDA) algorithm has been widely applied to solve minimax optimization problems. In order to achieve convergent policy parameters for minimax optimization, it is important that GDA generates convergent variable sequences rather than convergent sequences of function values or gradient norms. However, the variable convergence of GDA has been proved only under convexity geometries, and there lacks understanding for general nonconvex minimax optimization. This paper fills such a gap by studying the convergence of a more general proximal-GDA for regularized nonconvex-stro"},"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":"2102.04653","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-02-09T05:35:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3361e9ae325b51933a1391e2ee9d544482ae14811f127cfb495707c5d197b759","abstract_canon_sha256":"7ae050b9a1c868f1778b47c8dac8a3892ab960a951d2276a386689231befa2ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:16:01.860618Z","signature_b64":"+YJmGxraQ792imultwtDqDogDuxyB0BSjWkkNi9vynDZMsYZc5X9SFWBR4lblEXfJGQY225xPChdmYEK30h7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86490088d82f8f000abbdbcdb49f233ed94d5da7e3df2f7f3e5e65b74a6713ba","last_reissued_at":"2026-07-05T02:16:01.860125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:16:01.860125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proximal Gradient Descent-Ascent: Variable Convergence under K{\\L} Geometry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Tengyu Xu, Yingbin Liang, Yi Zhou, Ziyi Chen","submitted_at":"2021-02-09T05:35:53Z","abstract_excerpt":"The gradient descent-ascent (GDA) algorithm has been widely applied to solve minimax optimization problems. In order to achieve convergent policy parameters for minimax optimization, it is important that GDA generates convergent variable sequences rather than convergent sequences of function values or gradient norms. However, the variable convergence of GDA has been proved only under convexity geometries, and there lacks understanding for general nonconvex minimax optimization. This paper fills such a gap by studying the convergence of a more general proximal-GDA for regularized nonconvex-stro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04653","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/2102.04653/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":"2102.04653","created_at":"2026-07-05T02:16:01.860193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04653v2","created_at":"2026-07-05T02:16:01.860193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04653","created_at":"2026-07-05T02:16:01.860193+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZEQBCGYF6HQ","created_at":"2026-07-05T02:16:01.860193+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZEQBCGYF6HQACV3","created_at":"2026-07-05T02:16:01.860193+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZEQBCGY","created_at":"2026-07-05T02:16:01.860193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19050","citing_title":"First-Order Methods for Solving Convex (Strongly) Concave Minimax Problems with Functional Constraints","ref_index":274,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZEQBCGYF6HQACV33PG3JHZDH3","json":"https://pith.science/pith/QZEQBCGYF6HQACV33PG3JHZDH3.json","graph_json":"https://pith.science/api/pith-number/QZEQBCGYF6HQACV33PG3JHZDH3/graph.json","events_json":"https://pith.science/api/pith-number/QZEQBCGYF6HQACV33PG3JHZDH3/events.json","paper":"https://pith.science/paper/QZEQBCGY"},"agent_actions":{"view_html":"https://pith.science/pith/QZEQBCGYF6HQACV33PG3JHZDH3","download_json":"https://pith.science/pith/QZEQBCGYF6HQACV33PG3JHZDH3.json","view_paper":"https://pith.science/paper/QZEQBCGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04653&json=true","fetch_graph":"https://pith.science/api/pith-number/QZEQBCGYF6HQACV33PG3JHZDH3/graph.json","fetch_events":"https://pith.science/api/pith-number/QZEQBCGYF6HQACV33PG3JHZDH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZEQBCGYF6HQACV33PG3JHZDH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZEQBCGYF6HQACV33PG3JHZDH3/action/storage_attestation","attest_author":"https://pith.science/pith/QZEQBCGYF6HQACV33PG3JHZDH3/action/author_attestation","sign_citation":"https://pith.science/pith/QZEQBCGYF6HQACV33PG3JHZDH3/action/citation_signature","submit_replication":"https://pith.science/pith/QZEQBCGYF6HQACV33PG3JHZDH3/action/replication_record"}},"created_at":"2026-07-05T02:16:01.860193+00:00","updated_at":"2026-07-05T02:16:01.860193+00:00"}