{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OCRR3UIH23CPKUK7QPY6MZVL7S","short_pith_number":"pith:OCRR3UIH","schema_version":"1.0","canonical_sha256":"70a31dd107d6c4f5515f83f1e666abfc8ad5583643ec671b54041cc39d1839c0","source":{"kind":"arxiv","id":"2112.05604","version":1},"attestation_state":"computed","paper":{"title":"Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonio Orvieto, Aurelien Lucchi, Junchi Yang, Niao He","submitted_at":"2021-12-10T15:35:42Z","abstract_excerpt":"Gradient descent ascent (GDA), the simplest single-loop algorithm for nonconvex minimax optimization, is widely used in practical applications such as generative adversarial networks (GANs) and adversarial training. Albeit its desirable simplicity, recent work shows inferior convergence rates of GDA in theory even assuming strong concavity of the objective on one side. This paper establishes new convergence results for two alternative single-loop algorithms -- alternating GDA and smoothed GDA -- under the mild assumption that the objective satisfies the Polyak-Lojasiewicz (PL) condition about "},"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":"2112.05604","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-10T15:35:42Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"dea9f09701342db02b6ac5d274fd8e6a9245fd063b3a863b62e602863ce6a4e9","abstract_canon_sha256":"9d504c2011f04057434454a6a86e6ba726392cfb978c9909ba8bbcae3f630182"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:50.223147Z","signature_b64":"V0bTZwdHkIZmL2YgmIh0kk57N6HLwBgdWk+wVZCNJr9ePl+RMqtzl+UpzHymqHtBCDph4ZPO1RwJu0l/Ap9dCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70a31dd107d6c4f5515f83f1e666abfc8ad5583643ec671b54041cc39d1839c0","last_reissued_at":"2026-07-05T03:39:50.222756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:50.222756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonio Orvieto, Aurelien Lucchi, Junchi Yang, Niao He","submitted_at":"2021-12-10T15:35:42Z","abstract_excerpt":"Gradient descent ascent (GDA), the simplest single-loop algorithm for nonconvex minimax optimization, is widely used in practical applications such as generative adversarial networks (GANs) and adversarial training. Albeit its desirable simplicity, recent work shows inferior convergence rates of GDA in theory even assuming strong concavity of the objective on one side. This paper establishes new convergence results for two alternative single-loop algorithms -- alternating GDA and smoothed GDA -- under the mild assumption that the objective satisfies the Polyak-Lojasiewicz (PL) condition about "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05604","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.05604/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":"2112.05604","created_at":"2026-07-05T03:39:50.222814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.05604v1","created_at":"2026-07-05T03:39:50.222814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05604","created_at":"2026-07-05T03:39:50.222814+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCRR3UIH23CP","created_at":"2026-07-05T03:39:50.222814+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCRR3UIH23CPKUK7","created_at":"2026-07-05T03:39:50.222814+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCRR3UIH","created_at":"2026-07-05T03:39:50.222814+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/OCRR3UIH23CPKUK7QPY6MZVL7S","json":"https://pith.science/pith/OCRR3UIH23CPKUK7QPY6MZVL7S.json","graph_json":"https://pith.science/api/pith-number/OCRR3UIH23CPKUK7QPY6MZVL7S/graph.json","events_json":"https://pith.science/api/pith-number/OCRR3UIH23CPKUK7QPY6MZVL7S/events.json","paper":"https://pith.science/paper/OCRR3UIH"},"agent_actions":{"view_html":"https://pith.science/pith/OCRR3UIH23CPKUK7QPY6MZVL7S","download_json":"https://pith.science/pith/OCRR3UIH23CPKUK7QPY6MZVL7S.json","view_paper":"https://pith.science/paper/OCRR3UIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.05604&json=true","fetch_graph":"https://pith.science/api/pith-number/OCRR3UIH23CPKUK7QPY6MZVL7S/graph.json","fetch_events":"https://pith.science/api/pith-number/OCRR3UIH23CPKUK7QPY6MZVL7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCRR3UIH23CPKUK7QPY6MZVL7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCRR3UIH23CPKUK7QPY6MZVL7S/action/storage_attestation","attest_author":"https://pith.science/pith/OCRR3UIH23CPKUK7QPY6MZVL7S/action/author_attestation","sign_citation":"https://pith.science/pith/OCRR3UIH23CPKUK7QPY6MZVL7S/action/citation_signature","submit_replication":"https://pith.science/pith/OCRR3UIH23CPKUK7QPY6MZVL7S/action/replication_record"}},"created_at":"2026-07-05T03:39:50.222814+00:00","updated_at":"2026-07-05T03:39:50.222814+00:00"}