{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:X773IKO42CGPXVICHESU73LBRS","short_pith_number":"pith:X773IKO4","schema_version":"1.0","canonical_sha256":"bfffb429dcd08cfbd50239254fed618c8d77948331455f22b5c76603a1d7af0b","source":{"kind":"arxiv","id":"1803.01498","version":2},"attestation_state":"computed","paper":{"title":"Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dong Yin, Kannan Ramchandran, Peter Bartlett, Yudong Chen","submitted_at":"2018-03-05T05:04:17Z","abstract_excerpt":"In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and potentially adversarial behavior. In this paper, we develop distributed learning algorithms that are provably robust against such failures, with a focus on achieving optimal statistical performance. A main result of this work is a sharp analysis of two robust distributed gradient descent algorithms based on median and trimmed mean operations, respectively. We prove st"},"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":"1803.01498","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-05T05:04:17Z","cross_cats_sorted":["cs.CR","cs.DC","stat.ML"],"title_canon_sha256":"757242c8e4e4c5abf73f8cea2df44c585711020ce1fc235c5bd9ed7a4bcd6c16","abstract_canon_sha256":"3eb3f1e75ce59b849ac8868e29cf1cae93594b3470b67d2d36aeb033ed91eb83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:13.350412Z","signature_b64":"twuakRoQowdatIds85QCxVLV0wB76noXl9LgkypF4Gic+PH7KJGgmysSyswyUr+pjO2mQW4ttLi6WGPJ+tefDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfffb429dcd08cfbd50239254fed618c8d77948331455f22b5c76603a1d7af0b","last_reissued_at":"2026-07-05T02:18:13.349929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:13.349929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dong Yin, Kannan Ramchandran, Peter Bartlett, Yudong Chen","submitted_at":"2018-03-05T05:04:17Z","abstract_excerpt":"In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and potentially adversarial behavior. In this paper, we develop distributed learning algorithms that are provably robust against such failures, with a focus on achieving optimal statistical performance. A main result of this work is a sharp analysis of two robust distributed gradient descent algorithms based on median and trimmed mean operations, respectively. We prove st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01498","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/1803.01498/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":"1803.01498","created_at":"2026-07-05T02:18:13.349983+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.01498v2","created_at":"2026-07-05T02:18:13.349983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01498","created_at":"2026-07-05T02:18:13.349983+00:00"},{"alias_kind":"pith_short_12","alias_value":"X773IKO42CGP","created_at":"2026-07-05T02:18:13.349983+00:00"},{"alias_kind":"pith_short_16","alias_value":"X773IKO42CGPXVIC","created_at":"2026-07-05T02:18:13.349983+00:00"},{"alias_kind":"pith_short_8","alias_value":"X773IKO4","created_at":"2026-07-05T02:18:13.349983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.02707","citing_title":"Algorithms of Robust Stochastic Optimization Based on Mirror Descent Method","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2407.09658","citing_title":"BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X773IKO42CGPXVICHESU73LBRS","json":"https://pith.science/pith/X773IKO42CGPXVICHESU73LBRS.json","graph_json":"https://pith.science/api/pith-number/X773IKO42CGPXVICHESU73LBRS/graph.json","events_json":"https://pith.science/api/pith-number/X773IKO42CGPXVICHESU73LBRS/events.json","paper":"https://pith.science/paper/X773IKO4"},"agent_actions":{"view_html":"https://pith.science/pith/X773IKO42CGPXVICHESU73LBRS","download_json":"https://pith.science/pith/X773IKO42CGPXVICHESU73LBRS.json","view_paper":"https://pith.science/paper/X773IKO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.01498&json=true","fetch_graph":"https://pith.science/api/pith-number/X773IKO42CGPXVICHESU73LBRS/graph.json","fetch_events":"https://pith.science/api/pith-number/X773IKO42CGPXVICHESU73LBRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X773IKO42CGPXVICHESU73LBRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X773IKO42CGPXVICHESU73LBRS/action/storage_attestation","attest_author":"https://pith.science/pith/X773IKO42CGPXVICHESU73LBRS/action/author_attestation","sign_citation":"https://pith.science/pith/X773IKO42CGPXVICHESU73LBRS/action/citation_signature","submit_replication":"https://pith.science/pith/X773IKO42CGPXVICHESU73LBRS/action/replication_record"}},"created_at":"2026-07-05T02:18:13.349983+00:00","updated_at":"2026-07-05T02:18:13.349983+00:00"}