{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UZ674PQ4GEPMMD5T4USPWMT4BY","short_pith_number":"pith:UZ674PQ4","schema_version":"1.0","canonical_sha256":"a67dfe3e1c311ec60fb3e524fb327c0e3c022b25274c413a9f9ec9dc3f20501f","source":{"kind":"arxiv","id":"2503.08634","version":3},"attestation_state":"computed","paper":{"title":"Self-tuned Regularized Federated Methods with Guarantees for Optimal Solution Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Farzad Yousefian, Mohammadjavad Ebrahimi, Shisheng Cui, Yuyang Qiu","submitted_at":"2025-03-11T17:23:52Z","abstract_excerpt":"We study a hierarchical federated learning (FL) problem, where clients cooperatively seek to select among multiple optimal solutions of a primary distributed learning problem, a solution that minimizes a secondary loss function. This problem arises from over-parameterized learning and ill-posed optimization problems. First, we consider the setting where the inner-level objective is convex and the outer-level objective is either convex or strongly convex. We propose a self-tuned regularized federated averaging (StR-FedAvg) method where the stepsize and regularization parameter are characterized"},"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":"2503.08634","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-03-11T17:23:52Z","cross_cats_sorted":[],"title_canon_sha256":"8515c13fa7cc8b01e8a12bd44ed2552b5f4c451a15fac40af365053adc99b324","abstract_canon_sha256":"a991f1525c58eed36b5dbf887b0f53502624eca0f29b68ad766ed4e04ac92b7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:49.447293Z","signature_b64":"QKOwkkTuU4jRCBLphLLjXqYMjYueRqtGlyf0mwtEuNPhac1i3vPq12idQRMcwVlivnENN6pTFrGifLL/cuuLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a67dfe3e1c311ec60fb3e524fb327c0e3c022b25274c413a9f9ec9dc3f20501f","last_reissued_at":"2026-05-26T02:03:49.446266Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:49.446266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-tuned Regularized Federated Methods with Guarantees for Optimal Solution Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Farzad Yousefian, Mohammadjavad Ebrahimi, Shisheng Cui, Yuyang Qiu","submitted_at":"2025-03-11T17:23:52Z","abstract_excerpt":"We study a hierarchical federated learning (FL) problem, where clients cooperatively seek to select among multiple optimal solutions of a primary distributed learning problem, a solution that minimizes a secondary loss function. This problem arises from over-parameterized learning and ill-posed optimization problems. First, we consider the setting where the inner-level objective is convex and the outer-level objective is either convex or strongly convex. We propose a self-tuned regularized federated averaging (StR-FedAvg) method where the stepsize and regularization parameter are characterized"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08634","kind":"arxiv","version":3},"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/2503.08634/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":"2503.08634","created_at":"2026-05-26T02:03:49.446428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08634v3","created_at":"2026-05-26T02:03:49.446428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08634","created_at":"2026-05-26T02:03:49.446428+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZ674PQ4GEPM","created_at":"2026-05-26T02:03:49.446428+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZ674PQ4GEPMMD5T","created_at":"2026-05-26T02:03:49.446428+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZ674PQ4","created_at":"2026-05-26T02:03:49.446428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22916","citing_title":"On the Resolution of Stochastic MPECs over Networks: Distributed Implicit Zeroth-Order Gradient Tracking Methods","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZ674PQ4GEPMMD5T4USPWMT4BY","json":"https://pith.science/pith/UZ674PQ4GEPMMD5T4USPWMT4BY.json","graph_json":"https://pith.science/api/pith-number/UZ674PQ4GEPMMD5T4USPWMT4BY/graph.json","events_json":"https://pith.science/api/pith-number/UZ674PQ4GEPMMD5T4USPWMT4BY/events.json","paper":"https://pith.science/paper/UZ674PQ4"},"agent_actions":{"view_html":"https://pith.science/pith/UZ674PQ4GEPMMD5T4USPWMT4BY","download_json":"https://pith.science/pith/UZ674PQ4GEPMMD5T4USPWMT4BY.json","view_paper":"https://pith.science/paper/UZ674PQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08634&json=true","fetch_graph":"https://pith.science/api/pith-number/UZ674PQ4GEPMMD5T4USPWMT4BY/graph.json","fetch_events":"https://pith.science/api/pith-number/UZ674PQ4GEPMMD5T4USPWMT4BY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZ674PQ4GEPMMD5T4USPWMT4BY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZ674PQ4GEPMMD5T4USPWMT4BY/action/storage_attestation","attest_author":"https://pith.science/pith/UZ674PQ4GEPMMD5T4USPWMT4BY/action/author_attestation","sign_citation":"https://pith.science/pith/UZ674PQ4GEPMMD5T4USPWMT4BY/action/citation_signature","submit_replication":"https://pith.science/pith/UZ674PQ4GEPMMD5T4USPWMT4BY/action/replication_record"}},"created_at":"2026-05-26T02:03:49.446428+00:00","updated_at":"2026-05-26T02:03:49.446428+00:00"}