{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2ZU4MI6ZRTIQ6NJRDBFNI5GZNO","short_pith_number":"pith:2ZU4MI6Z","schema_version":"1.0","canonical_sha256":"d669c623d98cd10f3531184ad474d96bbcee46480743fe4bc325610c16d1e681","source":{"kind":"arxiv","id":"2405.14130","version":3},"attestation_state":"computed","paper":{"title":"High-probability complexity guarantees for nonconvex minimax problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Mert G\\\"urb\\\"uzbalaban, Necdet Serhat Aybat, Yasa Syed, Yassine Laguel","submitted_at":"2024-05-23T03:10:28Z","abstract_excerpt":"Stochastic smooth nonconvex minimax problems are prevalent in machine learning, e.g., GAN training, fair classification, and distributionally robust learning. Stochastic gradient descent ascent (GDA)-type methods are popular in practice due to their simplicity and single-loop nature. However, there is a significant gap between the theory and practice regarding high-probability complexity guarantees for these methods on stochastic nonconvex minimax problems. Existing high-probability bounds for GDA-type single-loop methods only apply to convex/concave minimax problems and to particular non-mono"},"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":"2405.14130","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-05-23T03:10:28Z","cross_cats_sorted":[],"title_canon_sha256":"5f2781c2bf14c7b420a82c145c1d1ae1e26dcf4547cfbcf678e2cc4e00104887","abstract_canon_sha256":"28708083452354924f31b11f4328660c7da3b54ddcaa22cb75d2629bf81afd1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:10.100425Z","signature_b64":"uAO9AS8DTOrDH8j1EPQ1HfDO7ZNujQ8o70B0XmFrrGGdXeCOpTWtxwNWHG4QNlSSY7s8T5Vbv/Vm1mSVvyiHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d669c623d98cd10f3531184ad474d96bbcee46480743fe4bc325610c16d1e681","last_reissued_at":"2026-07-05T09:35:10.099948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:10.099948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-probability complexity guarantees for nonconvex minimax problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Mert G\\\"urb\\\"uzbalaban, Necdet Serhat Aybat, Yasa Syed, Yassine Laguel","submitted_at":"2024-05-23T03:10:28Z","abstract_excerpt":"Stochastic smooth nonconvex minimax problems are prevalent in machine learning, e.g., GAN training, fair classification, and distributionally robust learning. Stochastic gradient descent ascent (GDA)-type methods are popular in practice due to their simplicity and single-loop nature. However, there is a significant gap between the theory and practice regarding high-probability complexity guarantees for these methods on stochastic nonconvex minimax problems. Existing high-probability bounds for GDA-type single-loop methods only apply to convex/concave minimax problems and to particular non-mono"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14130","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/2405.14130/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":"2405.14130","created_at":"2026-07-05T09:35:10.100001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14130v3","created_at":"2026-07-05T09:35:10.100001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14130","created_at":"2026-07-05T09:35:10.100001+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZU4MI6ZRTIQ","created_at":"2026-07-05T09:35:10.100001+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZU4MI6ZRTIQ6NJR","created_at":"2026-07-05T09:35:10.100001+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZU4MI6Z","created_at":"2026-07-05T09:35:10.100001+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/2ZU4MI6ZRTIQ6NJRDBFNI5GZNO","json":"https://pith.science/pith/2ZU4MI6ZRTIQ6NJRDBFNI5GZNO.json","graph_json":"https://pith.science/api/pith-number/2ZU4MI6ZRTIQ6NJRDBFNI5GZNO/graph.json","events_json":"https://pith.science/api/pith-number/2ZU4MI6ZRTIQ6NJRDBFNI5GZNO/events.json","paper":"https://pith.science/paper/2ZU4MI6Z"},"agent_actions":{"view_html":"https://pith.science/pith/2ZU4MI6ZRTIQ6NJRDBFNI5GZNO","download_json":"https://pith.science/pith/2ZU4MI6ZRTIQ6NJRDBFNI5GZNO.json","view_paper":"https://pith.science/paper/2ZU4MI6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14130&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZU4MI6ZRTIQ6NJRDBFNI5GZNO/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZU4MI6ZRTIQ6NJRDBFNI5GZNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZU4MI6ZRTIQ6NJRDBFNI5GZNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZU4MI6ZRTIQ6NJRDBFNI5GZNO/action/storage_attestation","attest_author":"https://pith.science/pith/2ZU4MI6ZRTIQ6NJRDBFNI5GZNO/action/author_attestation","sign_citation":"https://pith.science/pith/2ZU4MI6ZRTIQ6NJRDBFNI5GZNO/action/citation_signature","submit_replication":"https://pith.science/pith/2ZU4MI6ZRTIQ6NJRDBFNI5GZNO/action/replication_record"}},"created_at":"2026-07-05T09:35:10.100001+00:00","updated_at":"2026-07-05T09:35:10.100001+00:00"}