{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:N24YQVT7WTGUGAA4AKN3NH3ROK","short_pith_number":"pith:N24YQVT7","schema_version":"1.0","canonical_sha256":"6eb988567fb4cd43001c029bb69f7172ac8cf504c5e4991df6fc50981446ab93","source":{"kind":"arxiv","id":"2303.03984","version":4},"attestation_state":"computed","paper":{"title":"Enhanced Adaptive Gradient Algorithms for Nonconvex-PL Minimax Optimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Chunyu Xuan, Feihu Huang, Siqi Zhang, Songcan Chen, Xinrui Wang","submitted_at":"2023-03-07T15:33:12Z","abstract_excerpt":"Minimax optimization recently is widely applied in many machine learning tasks such as generative adversarial networks, robust learning and reinforcement learning. In the paper, we study a class of nonconvex-nonconcave minimax optimization with nonsmooth regularization, where the objective function is possibly nonconvex on primal variable $x$, and it is nonconcave and satisfies the Polyak-Lojasiewicz (PL) condition on dual variable $y$. Moreover, we propose a class of enhanced momentum-based gradient descent ascent methods (i.e., MSGDA and AdaMSGDA) to solve these stochastic nonconvex-PL minim"},"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":"2303.03984","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2023-03-07T15:33:12Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"title_canon_sha256":"b07e43149e0b97551d856c2d5019d6e6665e7094f9f1c937c25794051dd435d1","abstract_canon_sha256":"22328d2209829d1e4c4f194bfcc29361a7fce39e1cafe063ecf57fdf87b68327"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:08.525617Z","signature_b64":"3BpX1PS3T5d42mYPn1E15SnxkJr8SNK0H/K4XkMn9hsa5cCEw+HvS+jF13nNrafPcZkh5hCTkY4+JEsS/dsMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eb988567fb4cd43001c029bb69f7172ac8cf504c5e4991df6fc50981446ab93","last_reissued_at":"2026-07-05T10:52:08.525080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:08.525080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhanced Adaptive Gradient Algorithms for Nonconvex-PL Minimax Optimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Chunyu Xuan, Feihu Huang, Siqi Zhang, Songcan Chen, Xinrui Wang","submitted_at":"2023-03-07T15:33:12Z","abstract_excerpt":"Minimax optimization recently is widely applied in many machine learning tasks such as generative adversarial networks, robust learning and reinforcement learning. In the paper, we study a class of nonconvex-nonconcave minimax optimization with nonsmooth regularization, where the objective function is possibly nonconvex on primal variable $x$, and it is nonconcave and satisfies the Polyak-Lojasiewicz (PL) condition on dual variable $y$. Moreover, we propose a class of enhanced momentum-based gradient descent ascent methods (i.e., MSGDA and AdaMSGDA) to solve these stochastic nonconvex-PL minim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03984","kind":"arxiv","version":4},"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/2303.03984/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":"2303.03984","created_at":"2026-07-05T10:52:08.525148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03984v4","created_at":"2026-07-05T10:52:08.525148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03984","created_at":"2026-07-05T10:52:08.525148+00:00"},{"alias_kind":"pith_short_12","alias_value":"N24YQVT7WTGU","created_at":"2026-07-05T10:52:08.525148+00:00"},{"alias_kind":"pith_short_16","alias_value":"N24YQVT7WTGUGAA4","created_at":"2026-07-05T10:52:08.525148+00:00"},{"alias_kind":"pith_short_8","alias_value":"N24YQVT7","created_at":"2026-07-05T10:52:08.525148+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.01932","citing_title":"A first-order method for nonconvex-nonconcave minimax problems under a local Kurdyka-Lojasiewicz condition","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N24YQVT7WTGUGAA4AKN3NH3ROK","json":"https://pith.science/pith/N24YQVT7WTGUGAA4AKN3NH3ROK.json","graph_json":"https://pith.science/api/pith-number/N24YQVT7WTGUGAA4AKN3NH3ROK/graph.json","events_json":"https://pith.science/api/pith-number/N24YQVT7WTGUGAA4AKN3NH3ROK/events.json","paper":"https://pith.science/paper/N24YQVT7"},"agent_actions":{"view_html":"https://pith.science/pith/N24YQVT7WTGUGAA4AKN3NH3ROK","download_json":"https://pith.science/pith/N24YQVT7WTGUGAA4AKN3NH3ROK.json","view_paper":"https://pith.science/paper/N24YQVT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03984&json=true","fetch_graph":"https://pith.science/api/pith-number/N24YQVT7WTGUGAA4AKN3NH3ROK/graph.json","fetch_events":"https://pith.science/api/pith-number/N24YQVT7WTGUGAA4AKN3NH3ROK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N24YQVT7WTGUGAA4AKN3NH3ROK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N24YQVT7WTGUGAA4AKN3NH3ROK/action/storage_attestation","attest_author":"https://pith.science/pith/N24YQVT7WTGUGAA4AKN3NH3ROK/action/author_attestation","sign_citation":"https://pith.science/pith/N24YQVT7WTGUGAA4AKN3NH3ROK/action/citation_signature","submit_replication":"https://pith.science/pith/N24YQVT7WTGUGAA4AKN3NH3ROK/action/replication_record"}},"created_at":"2026-07-05T10:52:08.525148+00:00","updated_at":"2026-07-05T10:52:08.525148+00:00"}