{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BYEUPDCCZMZPLNC5YZ3WPUIAAW","short_pith_number":"pith:BYEUPDCC","schema_version":"1.0","canonical_sha256":"0e09478c42cb32f5b45dc67767d10005b808aadf02d9e57e3ac7dd39dc3ed84b","source":{"kind":"arxiv","id":"2102.07758","version":7},"attestation_state":"computed","paper":{"title":"Decentralized Distributed Optimization for Saddle Point Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"math.OC","authors_text":"Aleksandr Beznosikov, Alexander Gasnikov, Alexander Rogozin, Darina Dvinskikh, Dmitry Kovalev, Pavel Dvurechensky","submitted_at":"2021-02-15T18:55:58Z","abstract_excerpt":"We consider distributed convex-concave saddle point problems over arbitrary connected undirected networks and propose a decentralized distributed algorithm for their solution. The local functions distributed across the nodes are assumed to have global and local groups of variables. For the proposed algorithm we prove non-asymptotic convergence rate estimates with explicit dependence on the network characteristics. To supplement the convergence rate analysis, we propose lower bounds for strongly-convex-strongly-concave and convex-concave saddle-point problems over arbitrary connected undirected"},"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":"2102.07758","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-02-15T18:55:58Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"6e283a7c9d2894fd6f71e0397b47aeffd7e274fd6a8a1d81f6991ae787d97224","abstract_canon_sha256":"c04134b63c30e69b8d23af0416c254bc5cc5e05531b7fee4c9136bb597d4cc46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:45.602603Z","signature_b64":"rK22eZS0fj7md8qzzKrhAPwf1Cj1xYRM+vdmwrVtkpN/RbW2UX38WRVq0nOoycIJ/9/KlYBE5IWz1y2cvEOBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e09478c42cb32f5b45dc67767d10005b808aadf02d9e57e3ac7dd39dc3ed84b","last_reissued_at":"2026-07-05T08:05:45.602168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:45.602168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Distributed Optimization for Saddle Point Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"math.OC","authors_text":"Aleksandr Beznosikov, Alexander Gasnikov, Alexander Rogozin, Darina Dvinskikh, Dmitry Kovalev, Pavel Dvurechensky","submitted_at":"2021-02-15T18:55:58Z","abstract_excerpt":"We consider distributed convex-concave saddle point problems over arbitrary connected undirected networks and propose a decentralized distributed algorithm for their solution. The local functions distributed across the nodes are assumed to have global and local groups of variables. For the proposed algorithm we prove non-asymptotic convergence rate estimates with explicit dependence on the network characteristics. To supplement the convergence rate analysis, we propose lower bounds for strongly-convex-strongly-concave and convex-concave saddle-point problems over arbitrary connected undirected"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07758","kind":"arxiv","version":7},"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/2102.07758/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":"2102.07758","created_at":"2026-07-05T08:05:45.602230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.07758v7","created_at":"2026-07-05T08:05:45.602230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07758","created_at":"2026-07-05T08:05:45.602230+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYEUPDCCZMZP","created_at":"2026-07-05T08:05:45.602230+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYEUPDCCZMZPLNC5","created_at":"2026-07-05T08:05:45.602230+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYEUPDCC","created_at":"2026-07-05T08:05:45.602230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09411","citing_title":"Distributed Online Stochastic Convex-Concave Optimization: Dynamic Regret Analyses under Single and Multiple Consensus Steps","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BYEUPDCCZMZPLNC5YZ3WPUIAAW","json":"https://pith.science/pith/BYEUPDCCZMZPLNC5YZ3WPUIAAW.json","graph_json":"https://pith.science/api/pith-number/BYEUPDCCZMZPLNC5YZ3WPUIAAW/graph.json","events_json":"https://pith.science/api/pith-number/BYEUPDCCZMZPLNC5YZ3WPUIAAW/events.json","paper":"https://pith.science/paper/BYEUPDCC"},"agent_actions":{"view_html":"https://pith.science/pith/BYEUPDCCZMZPLNC5YZ3WPUIAAW","download_json":"https://pith.science/pith/BYEUPDCCZMZPLNC5YZ3WPUIAAW.json","view_paper":"https://pith.science/paper/BYEUPDCC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.07758&json=true","fetch_graph":"https://pith.science/api/pith-number/BYEUPDCCZMZPLNC5YZ3WPUIAAW/graph.json","fetch_events":"https://pith.science/api/pith-number/BYEUPDCCZMZPLNC5YZ3WPUIAAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYEUPDCCZMZPLNC5YZ3WPUIAAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYEUPDCCZMZPLNC5YZ3WPUIAAW/action/storage_attestation","attest_author":"https://pith.science/pith/BYEUPDCCZMZPLNC5YZ3WPUIAAW/action/author_attestation","sign_citation":"https://pith.science/pith/BYEUPDCCZMZPLNC5YZ3WPUIAAW/action/citation_signature","submit_replication":"https://pith.science/pith/BYEUPDCCZMZPLNC5YZ3WPUIAAW/action/replication_record"}},"created_at":"2026-07-05T08:05:45.602230+00:00","updated_at":"2026-07-05T08:05:45.602230+00:00"}