{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3FSEUGPVEZEOMQYZHG6HGWDYPC","short_pith_number":"pith:3FSEUGPV","schema_version":"1.0","canonical_sha256":"d9644a19f52648e6431939bc73587878bb9ae54818c269407204315bcfb0f699","source":{"kind":"arxiv","id":"2307.09421","version":2},"attestation_state":"computed","paper":{"title":"Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Gabriel Mancino-Ball, Necdet Serhat Aybat, Xuan Zhang, Yangyang Xu","submitted_at":"2023-07-18T16:42:53Z","abstract_excerpt":"We propose a novel single-loop decentralized algorithm called DGDA-VR for solving the stochastic nonconvex strongly-concave minimax problem over a connected network of $M$ agents. By using stochastic first-order oracles to estimate the local gradients, we prove that our algorithm finds an $\\epsilon$-accurate solution with $\\mathcal{O}(\\epsilon^{-3})$ sample complexity and $\\mathcal{O}(\\epsilon^{-2})$ communication complexity, both of which are optimal and match the lower bounds for this class of problems. Unlike competitors, our algorithm does not require multiple communications for the conver"},"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":"2307.09421","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-18T16:42:53Z","cross_cats_sorted":[],"title_canon_sha256":"3276c711b991e583bdc3cd2ac05bde93e4eed22ca8f7dfda67340233e36ef4df","abstract_canon_sha256":"e5ca3b43a3a4083e701d241420121f3f89860e1e9514f77e149b3c24f5e9b9f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:22.110423Z","signature_b64":"09XKCvMfrftsITpPzB5quJM0kpC3e8uGB4zjQ4+jcCrvUqJfDvzLLOzg0p1bel+aJ/ggTiXdV11/V/YuY7fjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9644a19f52648e6431939bc73587878bb9ae54818c269407204315bcfb0f699","last_reissued_at":"2026-07-05T07:58:22.109907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:22.109907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Gabriel Mancino-Ball, Necdet Serhat Aybat, Xuan Zhang, Yangyang Xu","submitted_at":"2023-07-18T16:42:53Z","abstract_excerpt":"We propose a novel single-loop decentralized algorithm called DGDA-VR for solving the stochastic nonconvex strongly-concave minimax problem over a connected network of $M$ agents. By using stochastic first-order oracles to estimate the local gradients, we prove that our algorithm finds an $\\epsilon$-accurate solution with $\\mathcal{O}(\\epsilon^{-3})$ sample complexity and $\\mathcal{O}(\\epsilon^{-2})$ communication complexity, both of which are optimal and match the lower bounds for this class of problems. Unlike competitors, our algorithm does not require multiple communications for the conver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09421","kind":"arxiv","version":2},"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/2307.09421/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":"2307.09421","created_at":"2026-07-05T07:58:22.109968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.09421v2","created_at":"2026-07-05T07:58:22.109968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09421","created_at":"2026-07-05T07:58:22.109968+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FSEUGPVEZEO","created_at":"2026-07-05T07:58:22.109968+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FSEUGPVEZEOMQYZ","created_at":"2026-07-05T07:58:22.109968+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FSEUGPV","created_at":"2026-07-05T07:58:22.109968+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":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3FSEUGPVEZEOMQYZHG6HGWDYPC","json":"https://pith.science/pith/3FSEUGPVEZEOMQYZHG6HGWDYPC.json","graph_json":"https://pith.science/api/pith-number/3FSEUGPVEZEOMQYZHG6HGWDYPC/graph.json","events_json":"https://pith.science/api/pith-number/3FSEUGPVEZEOMQYZHG6HGWDYPC/events.json","paper":"https://pith.science/paper/3FSEUGPV"},"agent_actions":{"view_html":"https://pith.science/pith/3FSEUGPVEZEOMQYZHG6HGWDYPC","download_json":"https://pith.science/pith/3FSEUGPVEZEOMQYZHG6HGWDYPC.json","view_paper":"https://pith.science/paper/3FSEUGPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.09421&json=true","fetch_graph":"https://pith.science/api/pith-number/3FSEUGPVEZEOMQYZHG6HGWDYPC/graph.json","fetch_events":"https://pith.science/api/pith-number/3FSEUGPVEZEOMQYZHG6HGWDYPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FSEUGPVEZEOMQYZHG6HGWDYPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FSEUGPVEZEOMQYZHG6HGWDYPC/action/storage_attestation","attest_author":"https://pith.science/pith/3FSEUGPVEZEOMQYZHG6HGWDYPC/action/author_attestation","sign_citation":"https://pith.science/pith/3FSEUGPVEZEOMQYZHG6HGWDYPC/action/citation_signature","submit_replication":"https://pith.science/pith/3FSEUGPVEZEOMQYZHG6HGWDYPC/action/replication_record"}},"created_at":"2026-07-05T07:58:22.109968+00:00","updated_at":"2026-07-05T07:58:22.109968+00:00"}