{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AKAD3BIJB63GGGFKKQZPDWJJJO","short_pith_number":"pith:AKAD3BIJ","schema_version":"1.0","canonical_sha256":"02803d85090fb66318aa5432f1d9294bad0f5d73a888cc2a49b69fdd42da467a","source":{"kind":"arxiv","id":"2010.13112","version":9},"attestation_state":"computed","paper":{"title":"Distributed Saddle-Point Problems: Lower Bounds, Near-Optimal and Robust Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Aleksandr Beznosikov, Alexander Gasnikov, Valentin Samokhin","submitted_at":"2020-10-25T13:13:44Z","abstract_excerpt":"This paper focuses on the distributed optimization of stochastic saddle point problems. The first part of the paper is devoted to lower bounds for the centralized and decentralized distributed methods for smooth (strongly) convex-(strongly) concave saddle point problems, as well as the near-optimal algorithms by which these bounds are achieved. Next, we present a new federated algorithm for centralized distributed saddle-point problems - Extra Step Local SGD. The theoretical analysis of the new method is carried out for strongly convex-strongly concave and non-convex-non-concave problems. In t"},"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":"2010.13112","kind":"arxiv","version":9},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-25T13:13:44Z","cross_cats_sorted":["cs.DC","math.OC"],"title_canon_sha256":"f3a4f6d35504d7b8dbf526ee26eeb3a3944731229e3b07652afc20a226ca24aa","abstract_canon_sha256":"754d242d949d2c316c521059cce9abb96a6110fa032b3c54dc5c97edee055c38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:41.749244Z","signature_b64":"AY4b8V2kAZDeZ4vRQUfyaB9sb7k/SD/GFdlUp51qd2kE4NONRLUNzmspNAo/zye/RjlrM6uqikCokboY+hMSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02803d85090fb66318aa5432f1d9294bad0f5d73a888cc2a49b69fdd42da467a","last_reissued_at":"2026-07-05T10:53:41.748759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:41.748759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Saddle-Point Problems: Lower Bounds, Near-Optimal and Robust Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Aleksandr Beznosikov, Alexander Gasnikov, Valentin Samokhin","submitted_at":"2020-10-25T13:13:44Z","abstract_excerpt":"This paper focuses on the distributed optimization of stochastic saddle point problems. The first part of the paper is devoted to lower bounds for the centralized and decentralized distributed methods for smooth (strongly) convex-(strongly) concave saddle point problems, as well as the near-optimal algorithms by which these bounds are achieved. Next, we present a new federated algorithm for centralized distributed saddle-point problems - Extra Step Local SGD. The theoretical analysis of the new method is carried out for strongly convex-strongly concave and non-convex-non-concave problems. In t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13112","kind":"arxiv","version":9},"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/2010.13112/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":"2010.13112","created_at":"2026-07-05T10:53:41.748811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.13112v9","created_at":"2026-07-05T10:53:41.748811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13112","created_at":"2026-07-05T10:53:41.748811+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKAD3BIJB63G","created_at":"2026-07-05T10:53:41.748811+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKAD3BIJB63GGGFK","created_at":"2026-07-05T10:53:41.748811+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKAD3BIJ","created_at":"2026-07-05T10:53:41.748811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.13428","citing_title":"Methods for Solving Variational Inequalities with Markovian Stochasticity","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22644","citing_title":"Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AKAD3BIJB63GGGFKKQZPDWJJJO","json":"https://pith.science/pith/AKAD3BIJB63GGGFKKQZPDWJJJO.json","graph_json":"https://pith.science/api/pith-number/AKAD3BIJB63GGGFKKQZPDWJJJO/graph.json","events_json":"https://pith.science/api/pith-number/AKAD3BIJB63GGGFKKQZPDWJJJO/events.json","paper":"https://pith.science/paper/AKAD3BIJ"},"agent_actions":{"view_html":"https://pith.science/pith/AKAD3BIJB63GGGFKKQZPDWJJJO","download_json":"https://pith.science/pith/AKAD3BIJB63GGGFKKQZPDWJJJO.json","view_paper":"https://pith.science/paper/AKAD3BIJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.13112&json=true","fetch_graph":"https://pith.science/api/pith-number/AKAD3BIJB63GGGFKKQZPDWJJJO/graph.json","fetch_events":"https://pith.science/api/pith-number/AKAD3BIJB63GGGFKKQZPDWJJJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKAD3BIJB63GGGFKKQZPDWJJJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKAD3BIJB63GGGFKKQZPDWJJJO/action/storage_attestation","attest_author":"https://pith.science/pith/AKAD3BIJB63GGGFKKQZPDWJJJO/action/author_attestation","sign_citation":"https://pith.science/pith/AKAD3BIJB63GGGFKKQZPDWJJJO/action/citation_signature","submit_replication":"https://pith.science/pith/AKAD3BIJB63GGGFKKQZPDWJJJO/action/replication_record"}},"created_at":"2026-07-05T10:53:41.748811+00:00","updated_at":"2026-07-05T10:53:41.748811+00:00"}