{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X4FAQ5CGKTOLSMZPERQUQCUQHJ","short_pith_number":"pith:X4FAQ5CG","schema_version":"1.0","canonical_sha256":"bf0a08744654dcb9332f2461480a903a7dcbfac13716af7209879e6f5666257b","source":{"kind":"arxiv","id":"2310.20369","version":1},"attestation_state":"computed","paper":{"title":"Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Bo Du, Dacheng Tao, Li Shen, Miaoxi Zhu","submitted_at":"2023-10-31T11:27:01Z","abstract_excerpt":"The growing size of available data has attracted increasing interest in solving minimax problems in a decentralized manner for various machine learning tasks. Previous theoretical research has primarily focused on the convergence rate and communication complexity of decentralized minimax algorithms, with little attention given to their generalization. In this paper, we investigate the primal-dual generalization bound of the decentralized stochastic gradient descent ascent (D-SGDA) algorithm using the approach of algorithmic stability under both convex-concave and nonconvex-nonconcave settings."},"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":"2310.20369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-31T11:27:01Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"310f8b93cfa28f87d76dcbae229817955b96f835f7fd45d29991418a462b205a","abstract_canon_sha256":"1ab08ae774060ba069cba0997cb44ce0bcf01651f17f230de8353cf6ec4b7ecb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:29.168031Z","signature_b64":"rTvzYZf1YgpqdWNIWMTEC55vBPFxmi5xWn2hI8eJEg6D4YamD+GhE+es685F7E76V3zM7kyH/nJiM1aktkIHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf0a08744654dcb9332f2461480a903a7dcbfac13716af7209879e6f5666257b","last_reissued_at":"2026-07-05T07:07:29.167575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:29.167575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Bo Du, Dacheng Tao, Li Shen, Miaoxi Zhu","submitted_at":"2023-10-31T11:27:01Z","abstract_excerpt":"The growing size of available data has attracted increasing interest in solving minimax problems in a decentralized manner for various machine learning tasks. Previous theoretical research has primarily focused on the convergence rate and communication complexity of decentralized minimax algorithms, with little attention given to their generalization. In this paper, we investigate the primal-dual generalization bound of the decentralized stochastic gradient descent ascent (D-SGDA) algorithm using the approach of algorithmic stability under both convex-concave and nonconvex-nonconcave settings."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20369","kind":"arxiv","version":1},"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/2310.20369/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":"2310.20369","created_at":"2026-07-05T07:07:29.167641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.20369v1","created_at":"2026-07-05T07:07:29.167641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20369","created_at":"2026-07-05T07:07:29.167641+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4FAQ5CGKTOL","created_at":"2026-07-05T07:07:29.167641+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4FAQ5CGKTOLSMZP","created_at":"2026-07-05T07:07:29.167641+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4FAQ5CG","created_at":"2026-07-05T07:07:29.167641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16081","citing_title":"Exploring the Generalization Capabilities of AID-based Bi-level Optimization","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4FAQ5CGKTOLSMZPERQUQCUQHJ","json":"https://pith.science/pith/X4FAQ5CGKTOLSMZPERQUQCUQHJ.json","graph_json":"https://pith.science/api/pith-number/X4FAQ5CGKTOLSMZPERQUQCUQHJ/graph.json","events_json":"https://pith.science/api/pith-number/X4FAQ5CGKTOLSMZPERQUQCUQHJ/events.json","paper":"https://pith.science/paper/X4FAQ5CG"},"agent_actions":{"view_html":"https://pith.science/pith/X4FAQ5CGKTOLSMZPERQUQCUQHJ","download_json":"https://pith.science/pith/X4FAQ5CGKTOLSMZPERQUQCUQHJ.json","view_paper":"https://pith.science/paper/X4FAQ5CG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.20369&json=true","fetch_graph":"https://pith.science/api/pith-number/X4FAQ5CGKTOLSMZPERQUQCUQHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/X4FAQ5CGKTOLSMZPERQUQCUQHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4FAQ5CGKTOLSMZPERQUQCUQHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4FAQ5CGKTOLSMZPERQUQCUQHJ/action/storage_attestation","attest_author":"https://pith.science/pith/X4FAQ5CGKTOLSMZPERQUQCUQHJ/action/author_attestation","sign_citation":"https://pith.science/pith/X4FAQ5CGKTOLSMZPERQUQCUQHJ/action/citation_signature","submit_replication":"https://pith.science/pith/X4FAQ5CGKTOLSMZPERQUQCUQHJ/action/replication_record"}},"created_at":"2026-07-05T07:07:29.167641+00:00","updated_at":"2026-07-05T07:07:29.167641+00:00"}