{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CXCR5ELDOEMNS6CY32VMNHVB3G","short_pith_number":"pith:CXCR5ELD","schema_version":"1.0","canonical_sha256":"15c51e91637118d97858deaac69ea1d9ab195f529b8cd2b51e90beac13ebbeeb","source":{"kind":"arxiv","id":"2207.06343","version":2},"attestation_state":"computed","paper":{"title":"TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Wei, Michael I. Jordan, Sai Praneeth Karimireddy, Yaodong Yu, Yi Ma","submitted_at":"2022-07-13T16:58:22Z","abstract_excerpt":"State-of-the-art federated learning methods can perform far worse than their centralized counterparts when clients have dissimilar data distributions. For neural networks, even when centralized SGD easily finds a solution that is simultaneously performant for all clients, current federated optimization methods fail to converge to a comparable solution. We show that this performance disparity can largely be attributed to optimization challenges presented by nonconvexity. Specifically, we find that the early layers of the network do learn useful features, but the final layers fail to make use of"},"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":"2207.06343","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T16:58:22Z","cross_cats_sorted":["cs.DC","math.OC","stat.ML"],"title_canon_sha256":"20d61e684966420d44a5a884ec5b3b2b59d0f0514d34fc8c4f25115cae69ae0f","abstract_canon_sha256":"dea8bbb59d49e8e3ef8bbc770de4c565da55c8c70fc1c7f6fe64754b6c571248"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:38.333463Z","signature_b64":"WYO+B/+tU9PtjvmakepvM5B3xb2s4oGfNtvaJpojKd7+HAh/qfW2FDyfLoxZW5AXuH2spWSRJY8ddxH3JuJYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15c51e91637118d97858deaac69ea1d9ab195f529b8cd2b51e90beac13ebbeeb","last_reissued_at":"2026-07-05T05:03:38.333018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:38.333018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Wei, Michael I. Jordan, Sai Praneeth Karimireddy, Yaodong Yu, Yi Ma","submitted_at":"2022-07-13T16:58:22Z","abstract_excerpt":"State-of-the-art federated learning methods can perform far worse than their centralized counterparts when clients have dissimilar data distributions. For neural networks, even when centralized SGD easily finds a solution that is simultaneously performant for all clients, current federated optimization methods fail to converge to a comparable solution. We show that this performance disparity can largely be attributed to optimization challenges presented by nonconvexity. Specifically, we find that the early layers of the network do learn useful features, but the final layers fail to make use of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06343","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/2207.06343/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":"2207.06343","created_at":"2026-07-05T05:03:38.333076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.06343v2","created_at":"2026-07-05T05:03:38.333076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06343","created_at":"2026-07-05T05:03:38.333076+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXCR5ELDOEMN","created_at":"2026-07-05T05:03:38.333076+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXCR5ELDOEMNS6CY","created_at":"2026-07-05T05:03:38.333076+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXCR5ELD","created_at":"2026-07-05T05:03:38.333076+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/CXCR5ELDOEMNS6CY32VMNHVB3G","json":"https://pith.science/pith/CXCR5ELDOEMNS6CY32VMNHVB3G.json","graph_json":"https://pith.science/api/pith-number/CXCR5ELDOEMNS6CY32VMNHVB3G/graph.json","events_json":"https://pith.science/api/pith-number/CXCR5ELDOEMNS6CY32VMNHVB3G/events.json","paper":"https://pith.science/paper/CXCR5ELD"},"agent_actions":{"view_html":"https://pith.science/pith/CXCR5ELDOEMNS6CY32VMNHVB3G","download_json":"https://pith.science/pith/CXCR5ELDOEMNS6CY32VMNHVB3G.json","view_paper":"https://pith.science/paper/CXCR5ELD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.06343&json=true","fetch_graph":"https://pith.science/api/pith-number/CXCR5ELDOEMNS6CY32VMNHVB3G/graph.json","fetch_events":"https://pith.science/api/pith-number/CXCR5ELDOEMNS6CY32VMNHVB3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXCR5ELDOEMNS6CY32VMNHVB3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXCR5ELDOEMNS6CY32VMNHVB3G/action/storage_attestation","attest_author":"https://pith.science/pith/CXCR5ELDOEMNS6CY32VMNHVB3G/action/author_attestation","sign_citation":"https://pith.science/pith/CXCR5ELDOEMNS6CY32VMNHVB3G/action/citation_signature","submit_replication":"https://pith.science/pith/CXCR5ELDOEMNS6CY32VMNHVB3G/action/replication_record"}},"created_at":"2026-07-05T05:03:38.333076+00:00","updated_at":"2026-07-05T05:03:38.333076+00:00"}