{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JIDWTWUVPBGCWVX6HHQMKS55EB","short_pith_number":"pith:JIDWTWUV","schema_version":"1.0","canonical_sha256":"4a0769da95784c2b56fe39e0c54bbd2057f1789cdb793b805337b7656ad31309","source":{"kind":"arxiv","id":"1909.04715","version":2},"attestation_state":"computed","paper":{"title":"First Analysis of Local GD on Heterogeneous Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.NA","math.NA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed Khaled, Konstantin Mishchenko, Peter Richt\\'arik","submitted_at":"2019-09-10T19:46:13Z","abstract_excerpt":"We provide the first convergence analysis of local gradient descent for minimizing the average of smooth and convex but otherwise arbitrary functions. Problems of this form and local gradient descent as a solution method are of importance in federated learning, where each function is based on private data stored by a user on a mobile device, and the data of different users can be arbitrarily heterogeneous. We show that in a low accuracy regime, the method has the same communication complexity as gradient descent."},"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":"1909.04715","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-10T19:46:13Z","cross_cats_sorted":["cs.DC","cs.NA","math.NA","math.OC","stat.ML"],"title_canon_sha256":"f4bdfba5ccd15e3bd5f6a851def8bd9949dff20a9c642cfea4284b728430bbfc","abstract_canon_sha256":"dd2f338a07139c8ca7a4639cd82186978dc657136ca20bd06237af36d3dbd061"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:48:59.993368Z","signature_b64":"AWZ2SwlVHZ2ngNgZN8F3dcJg/iUN3MNWVKM39vaCFmqQC1DrTIeVzeeJVY49S3PxJ3C1i+7aDrYlzQWbalbjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a0769da95784c2b56fe39e0c54bbd2057f1789cdb793b805337b7656ad31309","last_reissued_at":"2026-07-05T00:48:59.992908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:48:59.992908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"First Analysis of Local GD on Heterogeneous Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.NA","math.NA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed Khaled, Konstantin Mishchenko, Peter Richt\\'arik","submitted_at":"2019-09-10T19:46:13Z","abstract_excerpt":"We provide the first convergence analysis of local gradient descent for minimizing the average of smooth and convex but otherwise arbitrary functions. Problems of this form and local gradient descent as a solution method are of importance in federated learning, where each function is based on private data stored by a user on a mobile device, and the data of different users can be arbitrarily heterogeneous. We show that in a low accuracy regime, the method has the same communication complexity as gradient descent."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.04715","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/1909.04715/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":"1909.04715","created_at":"2026-07-05T00:48:59.992966+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.04715v2","created_at":"2026-07-05T00:48:59.992966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.04715","created_at":"2026-07-05T00:48:59.992966+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIDWTWUVPBGC","created_at":"2026-07-05T00:48:59.992966+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIDWTWUVPBGCWVX6","created_at":"2026-07-05T00:48:59.992966+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIDWTWUV","created_at":"2026-07-05T00:48:59.992966+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30930","citing_title":"SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2410.15368","citing_title":"Tighter Performance Theory of FedExProx","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2003.00295","citing_title":"Adaptive Federated Optimization","ref_index":221,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13434","citing_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JIDWTWUVPBGCWVX6HHQMKS55EB","json":"https://pith.science/pith/JIDWTWUVPBGCWVX6HHQMKS55EB.json","graph_json":"https://pith.science/api/pith-number/JIDWTWUVPBGCWVX6HHQMKS55EB/graph.json","events_json":"https://pith.science/api/pith-number/JIDWTWUVPBGCWVX6HHQMKS55EB/events.json","paper":"https://pith.science/paper/JIDWTWUV"},"agent_actions":{"view_html":"https://pith.science/pith/JIDWTWUVPBGCWVX6HHQMKS55EB","download_json":"https://pith.science/pith/JIDWTWUVPBGCWVX6HHQMKS55EB.json","view_paper":"https://pith.science/paper/JIDWTWUV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.04715&json=true","fetch_graph":"https://pith.science/api/pith-number/JIDWTWUVPBGCWVX6HHQMKS55EB/graph.json","fetch_events":"https://pith.science/api/pith-number/JIDWTWUVPBGCWVX6HHQMKS55EB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIDWTWUVPBGCWVX6HHQMKS55EB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIDWTWUVPBGCWVX6HHQMKS55EB/action/storage_attestation","attest_author":"https://pith.science/pith/JIDWTWUVPBGCWVX6HHQMKS55EB/action/author_attestation","sign_citation":"https://pith.science/pith/JIDWTWUVPBGCWVX6HHQMKS55EB/action/citation_signature","submit_replication":"https://pith.science/pith/JIDWTWUVPBGCWVX6HHQMKS55EB/action/replication_record"}},"created_at":"2026-07-05T00:48:59.992966+00:00","updated_at":"2026-07-05T00:48:59.992966+00:00"}