{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EQPPSPZJ435KGVLDZWXW52JTIQ","short_pith_number":"pith:EQPPSPZJ","schema_version":"1.0","canonical_sha256":"241ef93f29e6faa35563cdaf6ee9334438cd1dc14f73fb90489c314021169b27","source":{"kind":"arxiv","id":"2306.08393","version":2},"attestation_state":"computed","paper":{"title":"Provably Personalized and Robust Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Lie He, Mariel Werner, Martin Jaggi, Michael Jordan, Sai Praneeth Karimireddy","submitted_at":"2023-06-14T09:37:39Z","abstract_excerpt":"Identifying clients with similar objectives and learning a model-per-cluster is an intuitive and interpretable approach to personalization in federated learning. However, doing so with provable and optimal guarantees has remained an open challenge. We formalize this problem as a stochastic optimization problem, achieving optimal convergence rates for a large class of loss functions. We propose simple iterative algorithms which identify clusters of similar clients and train a personalized model-per-cluster, using local client gradients and flexible constraints on the clusters. The convergence r"},"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":"2306.08393","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-14T09:37:39Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"27b26c37c8c0641a077a099ad3eb795c95c86a90f7bce5358c47b60601929327","abstract_canon_sha256":"6df244de2cac61bacab56eec2424d79cc30159d304a9bec8a1bf5593da71520d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:50.994474Z","signature_b64":"zzjMnYBHojmEwdx8OuiYbv5mROhPIGG1o5qfReyHHosa+xCWIk+PPBIKxjfD8HvNZOKeiseWUMouZxa/UZ2NBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"241ef93f29e6faa35563cdaf6ee9334438cd1dc14f73fb90489c314021169b27","last_reissued_at":"2026-07-05T07:24:50.993978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:50.993978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Personalized and Robust Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Lie He, Mariel Werner, Martin Jaggi, Michael Jordan, Sai Praneeth Karimireddy","submitted_at":"2023-06-14T09:37:39Z","abstract_excerpt":"Identifying clients with similar objectives and learning a model-per-cluster is an intuitive and interpretable approach to personalization in federated learning. However, doing so with provable and optimal guarantees has remained an open challenge. We formalize this problem as a stochastic optimization problem, achieving optimal convergence rates for a large class of loss functions. We propose simple iterative algorithms which identify clusters of similar clients and train a personalized model-per-cluster, using local client gradients and flexible constraints on the clusters. The convergence r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08393","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/2306.08393/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":"2306.08393","created_at":"2026-07-05T07:24:50.994036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.08393v2","created_at":"2026-07-05T07:24:50.994036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08393","created_at":"2026-07-05T07:24:50.994036+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQPPSPZJ435K","created_at":"2026-07-05T07:24:50.994036+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQPPSPZJ435KGVLD","created_at":"2026-07-05T07:24:50.994036+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQPPSPZJ","created_at":"2026-07-05T07:24:50.994036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13287","citing_title":"Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQPPSPZJ435KGVLDZWXW52JTIQ","json":"https://pith.science/pith/EQPPSPZJ435KGVLDZWXW52JTIQ.json","graph_json":"https://pith.science/api/pith-number/EQPPSPZJ435KGVLDZWXW52JTIQ/graph.json","events_json":"https://pith.science/api/pith-number/EQPPSPZJ435KGVLDZWXW52JTIQ/events.json","paper":"https://pith.science/paper/EQPPSPZJ"},"agent_actions":{"view_html":"https://pith.science/pith/EQPPSPZJ435KGVLDZWXW52JTIQ","download_json":"https://pith.science/pith/EQPPSPZJ435KGVLDZWXW52JTIQ.json","view_paper":"https://pith.science/paper/EQPPSPZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.08393&json=true","fetch_graph":"https://pith.science/api/pith-number/EQPPSPZJ435KGVLDZWXW52JTIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EQPPSPZJ435KGVLDZWXW52JTIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQPPSPZJ435KGVLDZWXW52JTIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQPPSPZJ435KGVLDZWXW52JTIQ/action/storage_attestation","attest_author":"https://pith.science/pith/EQPPSPZJ435KGVLDZWXW52JTIQ/action/author_attestation","sign_citation":"https://pith.science/pith/EQPPSPZJ435KGVLDZWXW52JTIQ/action/citation_signature","submit_replication":"https://pith.science/pith/EQPPSPZJ435KGVLDZWXW52JTIQ/action/replication_record"}},"created_at":"2026-07-05T07:24:50.994036+00:00","updated_at":"2026-07-05T07:24:50.994036+00:00"}