{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PQ2NDQA7UKWS75SBN3QDRKTHXF","short_pith_number":"pith:PQ2NDQA7","schema_version":"1.0","canonical_sha256":"7c34d1c01fa2ad2ff6416ee038aa67b97fabe8e93d293913294823266ebd23e0","source":{"kind":"arxiv","id":"2310.11203","version":2},"attestation_state":"computed","paper":{"title":"Federated Learning with Nonvacuous Generalisation Bounds","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Guedj, Maxime Haddouche, Pierre Jobic","submitted_at":"2023-10-17T12:29:29Z","abstract_excerpt":"We introduce a novel strategy to train randomised predictors in federated learning, where each node of the network aims at preserving its privacy by releasing a local predictor but keeping secret its training dataset with respect to the other nodes.\n  We then build a global randomised predictor which inherits the properties of the local private predictors in the sense of a PAC-Bayesian generalisation bound. We consider the synchronous case where all nodes share the same training objective (derived from a generalisation bound), and the heterogenous and homogenous cases where each node may have "},"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":"2310.11203","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-17T12:29:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4c308e85d055d8efdccc64c727285dc7014b3b05bd3853be138a828cbf45cf77","abstract_canon_sha256":"754ec881303a0eca7258cb6b13dee4f3f3220708b921ce1c50546b691dbc2b61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:04:48.376037Z","signature_b64":"BhXhcegb8p8L6AaYl7FjcCOjHCPfBdn7+5vaQVtjDZlw3ZMCWOyFOaD5dt4HTarBx1uM3fFZB8t17+9gzyDVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c34d1c01fa2ad2ff6416ee038aa67b97fabe8e93d293913294823266ebd23e0","last_reissued_at":"2026-05-20T01:04:48.375220Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:04:48.375220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning with Nonvacuous Generalisation Bounds","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Guedj, Maxime Haddouche, Pierre Jobic","submitted_at":"2023-10-17T12:29:29Z","abstract_excerpt":"We introduce a novel strategy to train randomised predictors in federated learning, where each node of the network aims at preserving its privacy by releasing a local predictor but keeping secret its training dataset with respect to the other nodes.\n  We then build a global randomised predictor which inherits the properties of the local private predictors in the sense of a PAC-Bayesian generalisation bound. We consider the synchronous case where all nodes share the same training objective (derived from a generalisation bound), and the heterogenous and homogenous cases where each node may have "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11203","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/2310.11203/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":"2310.11203","created_at":"2026-05-20T01:04:48.375362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11203v2","created_at":"2026-05-20T01:04:48.375362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11203","created_at":"2026-05-20T01:04:48.375362+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQ2NDQA7UKWS","created_at":"2026-05-20T01:04:48.375362+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQ2NDQA7UKWS75SB","created_at":"2026-05-20T01:04:48.375362+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQ2NDQA7","created_at":"2026-05-20T01:04:48.375362+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/PQ2NDQA7UKWS75SBN3QDRKTHXF","json":"https://pith.science/pith/PQ2NDQA7UKWS75SBN3QDRKTHXF.json","graph_json":"https://pith.science/api/pith-number/PQ2NDQA7UKWS75SBN3QDRKTHXF/graph.json","events_json":"https://pith.science/api/pith-number/PQ2NDQA7UKWS75SBN3QDRKTHXF/events.json","paper":"https://pith.science/paper/PQ2NDQA7"},"agent_actions":{"view_html":"https://pith.science/pith/PQ2NDQA7UKWS75SBN3QDRKTHXF","download_json":"https://pith.science/pith/PQ2NDQA7UKWS75SBN3QDRKTHXF.json","view_paper":"https://pith.science/paper/PQ2NDQA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11203&json=true","fetch_graph":"https://pith.science/api/pith-number/PQ2NDQA7UKWS75SBN3QDRKTHXF/graph.json","fetch_events":"https://pith.science/api/pith-number/PQ2NDQA7UKWS75SBN3QDRKTHXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQ2NDQA7UKWS75SBN3QDRKTHXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQ2NDQA7UKWS75SBN3QDRKTHXF/action/storage_attestation","attest_author":"https://pith.science/pith/PQ2NDQA7UKWS75SBN3QDRKTHXF/action/author_attestation","sign_citation":"https://pith.science/pith/PQ2NDQA7UKWS75SBN3QDRKTHXF/action/citation_signature","submit_replication":"https://pith.science/pith/PQ2NDQA7UKWS75SBN3QDRKTHXF/action/replication_record"}},"created_at":"2026-05-20T01:04:48.375362+00:00","updated_at":"2026-05-20T01:04:48.375362+00:00"}