{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:55K6NE6RFLAH5VFVUCJR5PPTKH","short_pith_number":"pith:55K6NE6R","schema_version":"1.0","canonical_sha256":"ef55e693d12ac07ed4b5a0931ebdf351e7bdc16932c9dad2739610c6d4d64aaa","source":{"kind":"arxiv","id":"2202.08402","version":1},"attestation_state":"computed","paper":{"title":"Federated Stochastic Gradient Descent Begets Self-Induced Momentum","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Howard H. Yang, H. Vincent Poor, Tony Q. S. Quek, Yaru Fu, Zuozhu Liu","submitted_at":"2022-02-17T02:01:37Z","abstract_excerpt":"Federated learning (FL) is an emerging machine learning method that can be applied in mobile edge systems, in which a server and a host of clients collaboratively train a statistical model utilizing the data and computation resources of the clients without directly exposing their privacy-sensitive data. We show that running stochastic gradient descent (SGD) in such a setting can be viewed as adding a momentum-like term to the global aggregation process. Based on this finding, we further analyze the convergence rate of a federated learning system by accounting for the effects of parameter stale"},"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":"2202.08402","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-17T02:01:37Z","cross_cats_sorted":[],"title_canon_sha256":"b368e2a8fa26f2c3e0cef28ba89d98a55448f28fc77deb992884b08b9bcc1991","abstract_canon_sha256":"816cd5180fbb34413ce76d15856070362d0a65979c11ec44a0afef54d5f34a09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:45.479602Z","signature_b64":"StQ4Z6QOQo95YOmKS49XCy5EpwLclh108jqp5rnl38dWWaVNNysmt3baZOVViAVs/a/fst0QFdxLbT1D6a0jAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef55e693d12ac07ed4b5a0931ebdf351e7bdc16932c9dad2739610c6d4d64aaa","last_reissued_at":"2026-07-05T03:57:45.479058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:45.479058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Stochastic Gradient Descent Begets Self-Induced Momentum","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Howard H. Yang, H. Vincent Poor, Tony Q. S. Quek, Yaru Fu, Zuozhu Liu","submitted_at":"2022-02-17T02:01:37Z","abstract_excerpt":"Federated learning (FL) is an emerging machine learning method that can be applied in mobile edge systems, in which a server and a host of clients collaboratively train a statistical model utilizing the data and computation resources of the clients without directly exposing their privacy-sensitive data. We show that running stochastic gradient descent (SGD) in such a setting can be viewed as adding a momentum-like term to the global aggregation process. Based on this finding, we further analyze the convergence rate of a federated learning system by accounting for the effects of parameter stale"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.08402","kind":"arxiv","version":1},"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/2202.08402/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":"2202.08402","created_at":"2026-07-05T03:57:45.479123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.08402v1","created_at":"2026-07-05T03:57:45.479123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.08402","created_at":"2026-07-05T03:57:45.479123+00:00"},{"alias_kind":"pith_short_12","alias_value":"55K6NE6RFLAH","created_at":"2026-07-05T03:57:45.479123+00:00"},{"alias_kind":"pith_short_16","alias_value":"55K6NE6RFLAH5VFV","created_at":"2026-07-05T03:57:45.479123+00:00"},{"alias_kind":"pith_short_8","alias_value":"55K6NE6R","created_at":"2026-07-05T03:57:45.479123+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/55K6NE6RFLAH5VFVUCJR5PPTKH","json":"https://pith.science/pith/55K6NE6RFLAH5VFVUCJR5PPTKH.json","graph_json":"https://pith.science/api/pith-number/55K6NE6RFLAH5VFVUCJR5PPTKH/graph.json","events_json":"https://pith.science/api/pith-number/55K6NE6RFLAH5VFVUCJR5PPTKH/events.json","paper":"https://pith.science/paper/55K6NE6R"},"agent_actions":{"view_html":"https://pith.science/pith/55K6NE6RFLAH5VFVUCJR5PPTKH","download_json":"https://pith.science/pith/55K6NE6RFLAH5VFVUCJR5PPTKH.json","view_paper":"https://pith.science/paper/55K6NE6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.08402&json=true","fetch_graph":"https://pith.science/api/pith-number/55K6NE6RFLAH5VFVUCJR5PPTKH/graph.json","fetch_events":"https://pith.science/api/pith-number/55K6NE6RFLAH5VFVUCJR5PPTKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55K6NE6RFLAH5VFVUCJR5PPTKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55K6NE6RFLAH5VFVUCJR5PPTKH/action/storage_attestation","attest_author":"https://pith.science/pith/55K6NE6RFLAH5VFVUCJR5PPTKH/action/author_attestation","sign_citation":"https://pith.science/pith/55K6NE6RFLAH5VFVUCJR5PPTKH/action/citation_signature","submit_replication":"https://pith.science/pith/55K6NE6RFLAH5VFVUCJR5PPTKH/action/replication_record"}},"created_at":"2026-07-05T03:57:45.479123+00:00","updated_at":"2026-07-05T03:57:45.479123+00:00"}