{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NMZMSQZDEYYLIFGQT35R5Z74B3","short_pith_number":"pith:NMZMSQZD","schema_version":"1.0","canonical_sha256":"6b32c943232630b414d09efb1ee7fc0eef29b122fa897b87f1e16475aed067b5","source":{"kind":"arxiv","id":"2202.09674","version":2},"attestation_state":"computed","paper":{"title":"Generalized Optimistic Methods for Convex-Concave Saddle Point Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Aryan Mokhtari, Ruichen Jiang","submitted_at":"2022-02-19T20:31:05Z","abstract_excerpt":"The optimistic gradient method has seen increasing popularity for solving convex-concave saddle point problems. To analyze its iteration complexity, a recent work [arXiv:1906.01115] proposed an interesting perspective that interprets this method as an approximation to the proximal point method. In this paper, we follow this approach and distill the underlying idea of optimism to propose a generalized optimistic method, which includes the optimistic gradient method as a special case. Our general framework can handle constrained saddle point problems with composite objective functions and can wo"},"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":"2202.09674","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-02-19T20:31:05Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"fe4a00f6a5536a598cec194ba172b049a6bd527eeada6c88293c7c7a3851a61b","abstract_canon_sha256":"f42ca95c1b14fbffff51d21811a07e1239bdbba1b76607253e9a4b955a46a061"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:50.295959Z","signature_b64":"U2hBBkPHxvcdTyf6KmyTcGjbsi9gETOFvL36T7vFzmpV4W9hAKmcMl0BaIyV1vtYPN0iqVRMOt2ECUgPx4SCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b32c943232630b414d09efb1ee7fc0eef29b122fa897b87f1e16475aed067b5","last_reissued_at":"2026-07-05T07:31:50.295461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:50.295461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized Optimistic Methods for Convex-Concave Saddle Point Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Aryan Mokhtari, Ruichen Jiang","submitted_at":"2022-02-19T20:31:05Z","abstract_excerpt":"The optimistic gradient method has seen increasing popularity for solving convex-concave saddle point problems. To analyze its iteration complexity, a recent work [arXiv:1906.01115] proposed an interesting perspective that interprets this method as an approximation to the proximal point method. In this paper, we follow this approach and distill the underlying idea of optimism to propose a generalized optimistic method, which includes the optimistic gradient method as a special case. Our general framework can handle constrained saddle point problems with composite objective functions and can wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09674","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/2202.09674/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":"2202.09674","created_at":"2026-07-05T07:31:50.295525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.09674v2","created_at":"2026-07-05T07:31:50.295525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09674","created_at":"2026-07-05T07:31:50.295525+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMZMSQZDEYYL","created_at":"2026-07-05T07:31:50.295525+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMZMSQZDEYYLIFGQ","created_at":"2026-07-05T07:31:50.295525+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMZMSQZD","created_at":"2026-07-05T07:31:50.295525+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2403.07806","citing_title":"A Stochastic GDA Method With Backtracking For Solving Nonconvex Concave Minimax Problems","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19462","citing_title":"Solving Convex-Concave Problems with $\\tilde{\\mathcal{O}}(\\epsilon^{-4/(3p+1)})$ $p$th-Order Oracle Complexity","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NMZMSQZDEYYLIFGQT35R5Z74B3","json":"https://pith.science/pith/NMZMSQZDEYYLIFGQT35R5Z74B3.json","graph_json":"https://pith.science/api/pith-number/NMZMSQZDEYYLIFGQT35R5Z74B3/graph.json","events_json":"https://pith.science/api/pith-number/NMZMSQZDEYYLIFGQT35R5Z74B3/events.json","paper":"https://pith.science/paper/NMZMSQZD"},"agent_actions":{"view_html":"https://pith.science/pith/NMZMSQZDEYYLIFGQT35R5Z74B3","download_json":"https://pith.science/pith/NMZMSQZDEYYLIFGQT35R5Z74B3.json","view_paper":"https://pith.science/paper/NMZMSQZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.09674&json=true","fetch_graph":"https://pith.science/api/pith-number/NMZMSQZDEYYLIFGQT35R5Z74B3/graph.json","fetch_events":"https://pith.science/api/pith-number/NMZMSQZDEYYLIFGQT35R5Z74B3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMZMSQZDEYYLIFGQT35R5Z74B3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMZMSQZDEYYLIFGQT35R5Z74B3/action/storage_attestation","attest_author":"https://pith.science/pith/NMZMSQZDEYYLIFGQT35R5Z74B3/action/author_attestation","sign_citation":"https://pith.science/pith/NMZMSQZDEYYLIFGQT35R5Z74B3/action/citation_signature","submit_replication":"https://pith.science/pith/NMZMSQZDEYYLIFGQT35R5Z74B3/action/replication_record"}},"created_at":"2026-07-05T07:31:50.295525+00:00","updated_at":"2026-07-05T07:31:50.295525+00:00"}