{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BRDEC57UINRTKDUSYU76FK3B27","short_pith_number":"pith:BRDEC57U","schema_version":"1.0","canonical_sha256":"0c464177f44363350e92c53fe2ab61d7e120e6ecdec0aa0ff75723843abd4bee","source":{"kind":"arxiv","id":"2102.06333","version":1},"attestation_state":"computed","paper":{"title":"Efficient Algorithms for Federated Saddle Point Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Charlie Hou, Giulia Fanti, Kiran K. Thekumparampil, Sewoong Oh","submitted_at":"2021-02-12T02:55:36Z","abstract_excerpt":"We consider strongly convex-concave minimax problems in the federated setting, where the communication constraint is the main bottleneck. When clients are arbitrarily heterogeneous, a simple Minibatch Mirror-prox achieves the best performance. As the clients become more homogeneous, using multiple local gradient updates at the clients significantly improves upon Minibatch Mirror-prox by communicating less frequently. Our goal is to design an algorithm that can harness the benefit of similarity in the clients while recovering the Minibatch Mirror-prox performance under arbitrary heterogeneity ("},"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":"2102.06333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-12T02:55:36Z","cross_cats_sorted":["cs.DC","math.OC"],"title_canon_sha256":"5517420dbd4441ed64bfc3053d47f7a81e58f2e2f5fea9dbf9d3664068b5a2ef","abstract_canon_sha256":"d0ca25c7f519aa6a393ca0fce3fcb2aa4e38ae899b0308f8e4f708163773831f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:47.029017Z","signature_b64":"O4qpKMlq4VDP/5NbIHDHH/YihFuDUwDHWb8cX4fCr4tPrLH+ZqULTC0III3DryiohknCNyfN0x4B256JUbLwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c464177f44363350e92c53fe2ab61d7e120e6ecdec0aa0ff75723843abd4bee","last_reissued_at":"2026-07-05T02:14:47.028559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:47.028559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Algorithms for Federated Saddle Point Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Charlie Hou, Giulia Fanti, Kiran K. Thekumparampil, Sewoong Oh","submitted_at":"2021-02-12T02:55:36Z","abstract_excerpt":"We consider strongly convex-concave minimax problems in the federated setting, where the communication constraint is the main bottleneck. When clients are arbitrarily heterogeneous, a simple Minibatch Mirror-prox achieves the best performance. As the clients become more homogeneous, using multiple local gradient updates at the clients significantly improves upon Minibatch Mirror-prox by communicating less frequently. Our goal is to design an algorithm that can harness the benefit of similarity in the clients while recovering the Minibatch Mirror-prox performance under arbitrary heterogeneity ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.06333","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/2102.06333/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":"2102.06333","created_at":"2026-07-05T02:14:47.028621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.06333v1","created_at":"2026-07-05T02:14:47.028621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.06333","created_at":"2026-07-05T02:14:47.028621+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRDEC57UINRT","created_at":"2026-07-05T02:14:47.028621+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRDEC57UINRTKDUS","created_at":"2026-07-05T02:14:47.028621+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRDEC57U","created_at":"2026-07-05T02:14:47.028621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09365","citing_title":"Stability and Generalization for Distributed SGDA","ref_index":2012,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRDEC57UINRTKDUSYU76FK3B27","json":"https://pith.science/pith/BRDEC57UINRTKDUSYU76FK3B27.json","graph_json":"https://pith.science/api/pith-number/BRDEC57UINRTKDUSYU76FK3B27/graph.json","events_json":"https://pith.science/api/pith-number/BRDEC57UINRTKDUSYU76FK3B27/events.json","paper":"https://pith.science/paper/BRDEC57U"},"agent_actions":{"view_html":"https://pith.science/pith/BRDEC57UINRTKDUSYU76FK3B27","download_json":"https://pith.science/pith/BRDEC57UINRTKDUSYU76FK3B27.json","view_paper":"https://pith.science/paper/BRDEC57U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.06333&json=true","fetch_graph":"https://pith.science/api/pith-number/BRDEC57UINRTKDUSYU76FK3B27/graph.json","fetch_events":"https://pith.science/api/pith-number/BRDEC57UINRTKDUSYU76FK3B27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRDEC57UINRTKDUSYU76FK3B27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRDEC57UINRTKDUSYU76FK3B27/action/storage_attestation","attest_author":"https://pith.science/pith/BRDEC57UINRTKDUSYU76FK3B27/action/author_attestation","sign_citation":"https://pith.science/pith/BRDEC57UINRTKDUSYU76FK3B27/action/citation_signature","submit_replication":"https://pith.science/pith/BRDEC57UINRTKDUSYU76FK3B27/action/replication_record"}},"created_at":"2026-07-05T02:14:47.028621+00:00","updated_at":"2026-07-05T02:14:47.028621+00:00"}