{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KTN5TGHG32MTNHRASY4H7MA5Z5","short_pith_number":"pith:KTN5TGHG","schema_version":"1.0","canonical_sha256":"54dbd998e6de99369e2096387fb01dcf713593839fb05faa3ea3aa8f5c88979a","source":{"kind":"arxiv","id":"1901.08511","version":4},"attestation_state":"computed","paper":{"title":"A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Aryan Mokhtari, Asuman Ozdaglar, Sarath Pattathil","submitted_at":"2019-01-24T17:09:10Z","abstract_excerpt":"In this paper we consider solving saddle point problems using two variants of Gradient Descent-Ascent algorithms, Extra-gradient (EG) and Optimistic Gradient Descent Ascent (OGDA) methods. We show that both of these algorithms admit a unified analysis as approximations of the classical proximal point method for solving saddle point problems. This viewpoint enables us to develop a new framework for analyzing EG and OGDA for bilinear and strongly convex-strongly concave settings. Moreover, we use the proximal point approximation interpretation to generalize the results for OGDA for a wide range "},"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":"1901.08511","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-01-24T17:09:10Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"fb29e5533f0942fc34dcadc018e591d8fec7fd476957f41ba7118b3e0d847b66","abstract_canon_sha256":"063008152ca99f108e9cd0f6ab7bf19ded3e94084422f9d65b4d3988abd9ac23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:25.108483Z","signature_b64":"VsbzBvRcZVMy7z8ly2niyRx/JlJz3sUKAm6vtBxf0Rj3lEmmMClaPYVCWv7CpoUm4aG9fIYW1flUKslj+RXSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54dbd998e6de99369e2096387fb01dcf713593839fb05faa3ea3aa8f5c88979a","last_reissued_at":"2026-07-05T00:02:25.108103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:25.108103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Aryan Mokhtari, Asuman Ozdaglar, Sarath Pattathil","submitted_at":"2019-01-24T17:09:10Z","abstract_excerpt":"In this paper we consider solving saddle point problems using two variants of Gradient Descent-Ascent algorithms, Extra-gradient (EG) and Optimistic Gradient Descent Ascent (OGDA) methods. We show that both of these algorithms admit a unified analysis as approximations of the classical proximal point method for solving saddle point problems. This viewpoint enables us to develop a new framework for analyzing EG and OGDA for bilinear and strongly convex-strongly concave settings. Moreover, we use the proximal point approximation interpretation to generalize the results for OGDA for a wide range "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08511","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/1901.08511/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":"1901.08511","created_at":"2026-07-05T00:02:25.108166+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08511v4","created_at":"2026-07-05T00:02:25.108166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08511","created_at":"2026-07-05T00:02:25.108166+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTN5TGHG32MT","created_at":"2026-07-05T00:02:25.108166+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTN5TGHG32MTNHRA","created_at":"2026-07-05T00:02:25.108166+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTN5TGHG","created_at":"2026-07-05T00:02:25.108166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14371","citing_title":"Layer-wise Quantization for Quantized Optimistic Dual Averaging","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KTN5TGHG32MTNHRASY4H7MA5Z5","json":"https://pith.science/pith/KTN5TGHG32MTNHRASY4H7MA5Z5.json","graph_json":"https://pith.science/api/pith-number/KTN5TGHG32MTNHRASY4H7MA5Z5/graph.json","events_json":"https://pith.science/api/pith-number/KTN5TGHG32MTNHRASY4H7MA5Z5/events.json","paper":"https://pith.science/paper/KTN5TGHG"},"agent_actions":{"view_html":"https://pith.science/pith/KTN5TGHG32MTNHRASY4H7MA5Z5","download_json":"https://pith.science/pith/KTN5TGHG32MTNHRASY4H7MA5Z5.json","view_paper":"https://pith.science/paper/KTN5TGHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08511&json=true","fetch_graph":"https://pith.science/api/pith-number/KTN5TGHG32MTNHRASY4H7MA5Z5/graph.json","fetch_events":"https://pith.science/api/pith-number/KTN5TGHG32MTNHRASY4H7MA5Z5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTN5TGHG32MTNHRASY4H7MA5Z5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTN5TGHG32MTNHRASY4H7MA5Z5/action/storage_attestation","attest_author":"https://pith.science/pith/KTN5TGHG32MTNHRASY4H7MA5Z5/action/author_attestation","sign_citation":"https://pith.science/pith/KTN5TGHG32MTNHRASY4H7MA5Z5/action/citation_signature","submit_replication":"https://pith.science/pith/KTN5TGHG32MTNHRASY4H7MA5Z5/action/replication_record"}},"created_at":"2026-07-05T00:02:25.108166+00:00","updated_at":"2026-07-05T00:02:25.108166+00:00"}