{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WM3VJ7VNPNMLVBSAXGBD3OPIKJ","short_pith_number":"pith:WM3VJ7VN","schema_version":"1.0","canonical_sha256":"b33754fead7b58ba8640b9823db9e85277f0ff4b030f218d57b322b65c362225","source":{"kind":"arxiv","id":"2102.09468","version":3},"attestation_state":"computed","paper":{"title":"Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guodong Zhang, Laurent Lessard, Roger Grosse, Yuanhao Wang","submitted_at":"2021-02-18T16:39:35Z","abstract_excerpt":"Smooth minimax games often proceed by simultaneous or alternating gradient updates. Although algorithms with alternating updates are commonly used in practice, the majority of existing theoretical analyses focus on simultaneous algorithms for convenience of analysis. In this paper, we study alternating gradient descent-ascent (Alt-GDA) in minimax games and show that Alt-GDA is superior to its simultaneous counterpart~(Sim-GDA) in many settings. We prove that Alt-GDA achieves a near-optimal local convergence rate for strongly convex-strongly concave (SCSC) problems while Sim-GDA converges at a "},"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":"2102.09468","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-18T16:39:35Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"c5b2089732e72d4793edbc8b99ae81c5c8404f76e1d1ba53737b188a07eb57a3","abstract_canon_sha256":"dcd8c3f0bf64dd1dbae3c24e40b675b6c600c171113381ce19a0757378030f1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:28.425536Z","signature_b64":"lt1Bw+qh9mOsKGmTIMKg5G3hRJQ2cdsWf5+YF7mjewAzUG/OeizPpttgBPPsot/TKyiMkxu3pvslSlsFxhv0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b33754fead7b58ba8640b9823db9e85277f0ff4b030f218d57b322b65c362225","last_reissued_at":"2026-07-05T03:56:28.424877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:28.424877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guodong Zhang, Laurent Lessard, Roger Grosse, Yuanhao Wang","submitted_at":"2021-02-18T16:39:35Z","abstract_excerpt":"Smooth minimax games often proceed by simultaneous or alternating gradient updates. Although algorithms with alternating updates are commonly used in practice, the majority of existing theoretical analyses focus on simultaneous algorithms for convenience of analysis. In this paper, we study alternating gradient descent-ascent (Alt-GDA) in minimax games and show that Alt-GDA is superior to its simultaneous counterpart~(Sim-GDA) in many settings. We prove that Alt-GDA achieves a near-optimal local convergence rate for strongly convex-strongly concave (SCSC) problems while Sim-GDA converges at a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09468","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/2102.09468/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":"2102.09468","created_at":"2026-07-05T03:56:28.424963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.09468v3","created_at":"2026-07-05T03:56:28.424963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09468","created_at":"2026-07-05T03:56:28.424963+00:00"},{"alias_kind":"pith_short_12","alias_value":"WM3VJ7VNPNML","created_at":"2026-07-05T03:56:28.424963+00:00"},{"alias_kind":"pith_short_16","alias_value":"WM3VJ7VNPNMLVBSA","created_at":"2026-07-05T03:56:28.424963+00:00"},{"alias_kind":"pith_short_8","alias_value":"WM3VJ7VN","created_at":"2026-07-05T03:56:28.424963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14652","citing_title":"Decoupled SGDA for Games with Intermittent Strategy Communication","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WM3VJ7VNPNMLVBSAXGBD3OPIKJ","json":"https://pith.science/pith/WM3VJ7VNPNMLVBSAXGBD3OPIKJ.json","graph_json":"https://pith.science/api/pith-number/WM3VJ7VNPNMLVBSAXGBD3OPIKJ/graph.json","events_json":"https://pith.science/api/pith-number/WM3VJ7VNPNMLVBSAXGBD3OPIKJ/events.json","paper":"https://pith.science/paper/WM3VJ7VN"},"agent_actions":{"view_html":"https://pith.science/pith/WM3VJ7VNPNMLVBSAXGBD3OPIKJ","download_json":"https://pith.science/pith/WM3VJ7VNPNMLVBSAXGBD3OPIKJ.json","view_paper":"https://pith.science/paper/WM3VJ7VN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.09468&json=true","fetch_graph":"https://pith.science/api/pith-number/WM3VJ7VNPNMLVBSAXGBD3OPIKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WM3VJ7VNPNMLVBSAXGBD3OPIKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WM3VJ7VNPNMLVBSAXGBD3OPIKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WM3VJ7VNPNMLVBSAXGBD3OPIKJ/action/storage_attestation","attest_author":"https://pith.science/pith/WM3VJ7VNPNMLVBSAXGBD3OPIKJ/action/author_attestation","sign_citation":"https://pith.science/pith/WM3VJ7VNPNMLVBSAXGBD3OPIKJ/action/citation_signature","submit_replication":"https://pith.science/pith/WM3VJ7VNPNMLVBSAXGBD3OPIKJ/action/replication_record"}},"created_at":"2026-07-05T03:56:28.424963+00:00","updated_at":"2026-07-05T03:56:28.424963+00:00"}