{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4DXXRBSPG5YSSHX4M3DHN4F3XG","short_pith_number":"pith:4DXXRBSP","schema_version":"1.0","canonical_sha256":"e0ef78864f3771291efc66c676f0bbb9aff995e2e5066ca41542b8e6525f1023","source":{"kind":"arxiv","id":"2306.14012","version":2},"attestation_state":"computed","paper":{"title":"Private Networked Federated Learning for Nonsmooth Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Cristiano Gratton, Fran\\c{c}ois Gauthier, Naveen K. D. Venkategowda, Stefan Werner","submitted_at":"2023-06-24T16:13:28Z","abstract_excerpt":"This paper develops a networked federated learning algorithm to solve nonsmooth objective functions. To guarantee the confidentiality of the participants with respect to each other and potential eavesdroppers, we use the zero-concentrated differential privacy notion (zCDP). Privacy is achieved by perturbing the outcome of the computation at each client with a variance-decreasing Gaussian noise. ZCDP allows for better accuracy than the conventional $(\\epsilon, \\delta)$-DP and stronger guarantees than the more recent R\\'enyi-DP by assuming adversaries aggregate all the exchanged messages. The pr"},"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":"2306.14012","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-06-24T16:13:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"802cb5084434ede5964859231e3748a15c5e184571c1e69b958875d5f888a340","abstract_canon_sha256":"3cd54d7ab6069200b71596506f72b20ada3776a40a83048e6677647c4f876964"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:43.611566Z","signature_b64":"QzDzc5V2TeIiMzIaLcGsw6O9kxLFFZlaC2DzIkkcpGsdJW5qZHRK3MjSSmDwRkqpJWpSVO7ekr87ymzZ0WxIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0ef78864f3771291efc66c676f0bbb9aff995e2e5066ca41542b8e6525f1023","last_reissued_at":"2026-07-05T07:47:43.610976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:43.610976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Private Networked Federated Learning for Nonsmooth Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Cristiano Gratton, Fran\\c{c}ois Gauthier, Naveen K. D. Venkategowda, Stefan Werner","submitted_at":"2023-06-24T16:13:28Z","abstract_excerpt":"This paper develops a networked federated learning algorithm to solve nonsmooth objective functions. To guarantee the confidentiality of the participants with respect to each other and potential eavesdroppers, we use the zero-concentrated differential privacy notion (zCDP). Privacy is achieved by perturbing the outcome of the computation at each client with a variance-decreasing Gaussian noise. ZCDP allows for better accuracy than the conventional $(\\epsilon, \\delta)$-DP and stronger guarantees than the more recent R\\'enyi-DP by assuming adversaries aggregate all the exchanged messages. The pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14012","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/2306.14012/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":"2306.14012","created_at":"2026-07-05T07:47:43.611043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14012v2","created_at":"2026-07-05T07:47:43.611043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14012","created_at":"2026-07-05T07:47:43.611043+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DXXRBSPG5YS","created_at":"2026-07-05T07:47:43.611043+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DXXRBSPG5YSSHX4","created_at":"2026-07-05T07:47:43.611043+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DXXRBSP","created_at":"2026-07-05T07:47:43.611043+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/4DXXRBSPG5YSSHX4M3DHN4F3XG","json":"https://pith.science/pith/4DXXRBSPG5YSSHX4M3DHN4F3XG.json","graph_json":"https://pith.science/api/pith-number/4DXXRBSPG5YSSHX4M3DHN4F3XG/graph.json","events_json":"https://pith.science/api/pith-number/4DXXRBSPG5YSSHX4M3DHN4F3XG/events.json","paper":"https://pith.science/paper/4DXXRBSP"},"agent_actions":{"view_html":"https://pith.science/pith/4DXXRBSPG5YSSHX4M3DHN4F3XG","download_json":"https://pith.science/pith/4DXXRBSPG5YSSHX4M3DHN4F3XG.json","view_paper":"https://pith.science/paper/4DXXRBSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14012&json=true","fetch_graph":"https://pith.science/api/pith-number/4DXXRBSPG5YSSHX4M3DHN4F3XG/graph.json","fetch_events":"https://pith.science/api/pith-number/4DXXRBSPG5YSSHX4M3DHN4F3XG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DXXRBSPG5YSSHX4M3DHN4F3XG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DXXRBSPG5YSSHX4M3DHN4F3XG/action/storage_attestation","attest_author":"https://pith.science/pith/4DXXRBSPG5YSSHX4M3DHN4F3XG/action/author_attestation","sign_citation":"https://pith.science/pith/4DXXRBSPG5YSSHX4M3DHN4F3XG/action/citation_signature","submit_replication":"https://pith.science/pith/4DXXRBSPG5YSSHX4M3DHN4F3XG/action/replication_record"}},"created_at":"2026-07-05T07:47:43.611043+00:00","updated_at":"2026-07-05T07:47:43.611043+00:00"}