{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GEFIID2NGLOYQTAMIIM74VZPFT","short_pith_number":"pith:GEFIID2N","schema_version":"1.0","canonical_sha256":"310a840f4d32dd884c0c4219fe572f2cd2e9a37dbc5a33b29b8119348e70092b","source":{"kind":"arxiv","id":"2111.12743","version":4},"attestation_state":"computed","paper":{"title":"Robust Accelerated Primal-Dual Methods for Computing Saddle Points","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, Xuan Zhang","submitted_at":"2021-11-24T19:03:44Z","abstract_excerpt":"We consider strongly-convex-strongly-concave saddle point problems assuming we have access to unbiased stochastic estimates of the gradients. We propose a stochastic accelerated primal-dual (SAPD) algorithm and show that SAPD sequence, generated using constant primal-dual step sizes, linearly converges to a neighborhood of the unique saddle point. Interpreting the size of the neighborhood as a measure of robustness to gradient noise, we obtain explicit characterizations of robustness in terms of SAPD parameters and problem constants. Based on these characterizations, we develop computationally"},"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":"2111.12743","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-11-24T19:03:44Z","cross_cats_sorted":[],"title_canon_sha256":"c1b8cca11b8f6736cdae2e7fa463f2e62de67868a9a7f785e069b30a93379a8d","abstract_canon_sha256":"93062e4a0d347d90a54eaa37b19f327f1cf83c6bb971691731924acda3695429"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:20.994143Z","signature_b64":"w9T2Vrd7Y2IifmOC2OCieRgqMAy5l49xYNgPMWZLDSvPJM78B8evlHKxNCKV0RAwbURT3/DGdoms3hpQoVr9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"310a840f4d32dd884c0c4219fe572f2cd2e9a37dbc5a33b29b8119348e70092b","last_reissued_at":"2026-07-05T09:01:20.993725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:20.993725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Accelerated Primal-Dual Methods for Computing Saddle Points","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, Xuan Zhang","submitted_at":"2021-11-24T19:03:44Z","abstract_excerpt":"We consider strongly-convex-strongly-concave saddle point problems assuming we have access to unbiased stochastic estimates of the gradients. We propose a stochastic accelerated primal-dual (SAPD) algorithm and show that SAPD sequence, generated using constant primal-dual step sizes, linearly converges to a neighborhood of the unique saddle point. Interpreting the size of the neighborhood as a measure of robustness to gradient noise, we obtain explicit characterizations of robustness in terms of SAPD parameters and problem constants. Based on these characterizations, we develop computationally"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12743","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/2111.12743/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":"2111.12743","created_at":"2026-07-05T09:01:20.993778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.12743v4","created_at":"2026-07-05T09:01:20.993778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12743","created_at":"2026-07-05T09:01:20.993778+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEFIID2NGLOY","created_at":"2026-07-05T09:01:20.993778+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEFIID2NGLOYQTAM","created_at":"2026-07-05T09:01:20.993778+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEFIID2N","created_at":"2026-07-05T09:01:20.993778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GEFIID2NGLOYQTAMIIM74VZPFT","json":"https://pith.science/pith/GEFIID2NGLOYQTAMIIM74VZPFT.json","graph_json":"https://pith.science/api/pith-number/GEFIID2NGLOYQTAMIIM74VZPFT/graph.json","events_json":"https://pith.science/api/pith-number/GEFIID2NGLOYQTAMIIM74VZPFT/events.json","paper":"https://pith.science/paper/GEFIID2N"},"agent_actions":{"view_html":"https://pith.science/pith/GEFIID2NGLOYQTAMIIM74VZPFT","download_json":"https://pith.science/pith/GEFIID2NGLOYQTAMIIM74VZPFT.json","view_paper":"https://pith.science/paper/GEFIID2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.12743&json=true","fetch_graph":"https://pith.science/api/pith-number/GEFIID2NGLOYQTAMIIM74VZPFT/graph.json","fetch_events":"https://pith.science/api/pith-number/GEFIID2NGLOYQTAMIIM74VZPFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEFIID2NGLOYQTAMIIM74VZPFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEFIID2NGLOYQTAMIIM74VZPFT/action/storage_attestation","attest_author":"https://pith.science/pith/GEFIID2NGLOYQTAMIIM74VZPFT/action/author_attestation","sign_citation":"https://pith.science/pith/GEFIID2NGLOYQTAMIIM74VZPFT/action/citation_signature","submit_replication":"https://pith.science/pith/GEFIID2NGLOYQTAMIIM74VZPFT/action/replication_record"}},"created_at":"2026-07-05T09:01:20.993778+00:00","updated_at":"2026-07-05T09:01:20.993778+00:00"}