{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2XVTACTCGFPTTI2ST4T5JSDSJC","short_pith_number":"pith:2XVTACTC","schema_version":"1.0","canonical_sha256":"d5eb300a62315f39a3529f27d4c87248a223703ca89e5d37861ec4118ccc66bb","source":{"kind":"arxiv","id":"2605.18656","version":1},"attestation_state":"computed","paper":{"title":"Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Arnab Auddy, Subhadeep Paul, Xiangni Peng","submitted_at":"2026-05-18T17:01:34Z","abstract_excerpt":"Federated Learning is a leading framework for training ML and AI models collaboratively across numerous user devices or databases. We study the trade-offs among estimation accuracy, privacy constraints, and communication cost for differentially private (DP) federated M estimation. The two standard methods in the literature are FedAvg, which may suffer from high federation bias, and FedSGD, which can incur high communication cost. Aimed at improving accuracy at a reduced communication cost, we propose FedHybrid, which uses FedSGD starting with an improved initialization by the FedAvg estimator."},"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":"2605.18656","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T17:01:34Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ME"],"title_canon_sha256":"5caa0f260f69861d5bcdb89d4c26ef50160bbeaa30aac578b0d9c94e2097c59d","abstract_canon_sha256":"b4f8bf887e4a25216dd3acf6b82d554da5e10222269ad30abb7c0b5bea9c641f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:13.101815Z","signature_b64":"1HD1wMUCO98XerP04AhL70TcQ6sK+nMSUiTeUUHLf2Vhc7bgyj8VGLMZK7uSZSC/lUfF9opn5MwVPiPwE8IcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5eb300a62315f39a3529f27d4c87248a223703ca89e5d37861ec4118ccc66bb","last_reissued_at":"2026-05-20T00:06:13.100855Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:13.100855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Arnab Auddy, Subhadeep Paul, Xiangni Peng","submitted_at":"2026-05-18T17:01:34Z","abstract_excerpt":"Federated Learning is a leading framework for training ML and AI models collaboratively across numerous user devices or databases. We study the trade-offs among estimation accuracy, privacy constraints, and communication cost for differentially private (DP) federated M estimation. The two standard methods in the literature are FedAvg, which may suffer from high federation bias, and FedSGD, which can incur high communication cost. Aimed at improving accuracy at a reduced communication cost, we propose FedHybrid, which uses FedSGD starting with an improved initialization by the FedAvg estimator."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18656","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/2605.18656/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.159478Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"328c3c403b9b4ce24cf36e7936fc0a14a3f9cd0883810ee2738cc6c407296baf"},"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":"2605.18656","created_at":"2026-05-20T00:06:13.101119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18656v1","created_at":"2026-05-20T00:06:13.101119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18656","created_at":"2026-05-20T00:06:13.101119+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XVTACTCGFPT","created_at":"2026-05-20T00:06:13.101119+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XVTACTCGFPTTI2S","created_at":"2026-05-20T00:06:13.101119+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XVTACTC","created_at":"2026-05-20T00:06:13.101119+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2XVTACTCGFPTTI2ST4T5JSDSJC","json":"https://pith.science/pith/2XVTACTCGFPTTI2ST4T5JSDSJC.json","graph_json":"https://pith.science/api/pith-number/2XVTACTCGFPTTI2ST4T5JSDSJC/graph.json","events_json":"https://pith.science/api/pith-number/2XVTACTCGFPTTI2ST4T5JSDSJC/events.json","paper":"https://pith.science/paper/2XVTACTC"},"agent_actions":{"view_html":"https://pith.science/pith/2XVTACTCGFPTTI2ST4T5JSDSJC","download_json":"https://pith.science/pith/2XVTACTCGFPTTI2ST4T5JSDSJC.json","view_paper":"https://pith.science/paper/2XVTACTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18656&json=true","fetch_graph":"https://pith.science/api/pith-number/2XVTACTCGFPTTI2ST4T5JSDSJC/graph.json","fetch_events":"https://pith.science/api/pith-number/2XVTACTCGFPTTI2ST4T5JSDSJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XVTACTCGFPTTI2ST4T5JSDSJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XVTACTCGFPTTI2ST4T5JSDSJC/action/storage_attestation","attest_author":"https://pith.science/pith/2XVTACTCGFPTTI2ST4T5JSDSJC/action/author_attestation","sign_citation":"https://pith.science/pith/2XVTACTCGFPTTI2ST4T5JSDSJC/action/citation_signature","submit_replication":"https://pith.science/pith/2XVTACTCGFPTTI2ST4T5JSDSJC/action/replication_record"}},"created_at":"2026-05-20T00:06:13.101119+00:00","updated_at":"2026-05-20T00:06:13.101119+00:00"}