{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SMGYFG4NZYUV23TW42J2GV2TDS","short_pith_number":"pith:SMGYFG4N","schema_version":"1.0","canonical_sha256":"930d829b8dce295d6e76e693a357531ca1ef812deb5c471eaa06d9c5676d6d09","source":{"kind":"arxiv","id":"2205.06491","version":4},"attestation_state":"computed","paper":{"title":"Tighter Regret Analysis and Optimization of Online Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dohyeok Kwon, Jonghwan Park, Songnam Hong","submitted_at":"2022-05-13T07:46:43Z","abstract_excerpt":"In federated learning (FL), it is commonly assumed that all data are placed at clients in the beginning of machine learning (ML) optimization (i.e., offline learning). However, in many real-world applications, it is expected to proceed in an online fashion. To this end, online FL (OFL) has been introduced, which aims at learning a sequence of global models from decentralized streaming data such that the so-called cumulative regret is minimized. Combining online gradient descent and model averaging, in this framework, FedOGD is constructed as the counterpart of FedSGD in FL. While it can enjoy "},"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":"2205.06491","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-13T07:46:43Z","cross_cats_sorted":[],"title_canon_sha256":"1b9910dc61d23c14cb102ae4ad984ca932e335cba39c045cbb744510633f70d5","abstract_canon_sha256":"f4108ea1960e8f096d4dd64b12744448818293946c261213b6838768878702e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:15.134509Z","signature_b64":"VfkayFxgRwTtYEjnl7g0CiqtOPnmtx2cWN7QhfZl2ech48VfAJ32imKcb5pyEtbGUFVCA0XPDMvqXtQ5xby4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"930d829b8dce295d6e76e693a357531ca1ef812deb5c471eaa06d9c5676d6d09","last_reissued_at":"2026-07-05T05:34:15.134024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:15.134024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tighter Regret Analysis and Optimization of Online Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dohyeok Kwon, Jonghwan Park, Songnam Hong","submitted_at":"2022-05-13T07:46:43Z","abstract_excerpt":"In federated learning (FL), it is commonly assumed that all data are placed at clients in the beginning of machine learning (ML) optimization (i.e., offline learning). However, in many real-world applications, it is expected to proceed in an online fashion. To this end, online FL (OFL) has been introduced, which aims at learning a sequence of global models from decentralized streaming data such that the so-called cumulative regret is minimized. Combining online gradient descent and model averaging, in this framework, FedOGD is constructed as the counterpart of FedSGD in FL. While it can enjoy "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06491","kind":"arxiv","version":4},"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/2205.06491/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":"2205.06491","created_at":"2026-07-05T05:34:15.134082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.06491v4","created_at":"2026-07-05T05:34:15.134082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06491","created_at":"2026-07-05T05:34:15.134082+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMGYFG4NZYUV","created_at":"2026-07-05T05:34:15.134082+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMGYFG4NZYUV23TW","created_at":"2026-07-05T05:34:15.134082+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMGYFG4N","created_at":"2026-07-05T05:34:15.134082+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/SMGYFG4NZYUV23TW42J2GV2TDS","json":"https://pith.science/pith/SMGYFG4NZYUV23TW42J2GV2TDS.json","graph_json":"https://pith.science/api/pith-number/SMGYFG4NZYUV23TW42J2GV2TDS/graph.json","events_json":"https://pith.science/api/pith-number/SMGYFG4NZYUV23TW42J2GV2TDS/events.json","paper":"https://pith.science/paper/SMGYFG4N"},"agent_actions":{"view_html":"https://pith.science/pith/SMGYFG4NZYUV23TW42J2GV2TDS","download_json":"https://pith.science/pith/SMGYFG4NZYUV23TW42J2GV2TDS.json","view_paper":"https://pith.science/paper/SMGYFG4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.06491&json=true","fetch_graph":"https://pith.science/api/pith-number/SMGYFG4NZYUV23TW42J2GV2TDS/graph.json","fetch_events":"https://pith.science/api/pith-number/SMGYFG4NZYUV23TW42J2GV2TDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMGYFG4NZYUV23TW42J2GV2TDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMGYFG4NZYUV23TW42J2GV2TDS/action/storage_attestation","attest_author":"https://pith.science/pith/SMGYFG4NZYUV23TW42J2GV2TDS/action/author_attestation","sign_citation":"https://pith.science/pith/SMGYFG4NZYUV23TW42J2GV2TDS/action/citation_signature","submit_replication":"https://pith.science/pith/SMGYFG4NZYUV23TW42J2GV2TDS/action/replication_record"}},"created_at":"2026-07-05T05:34:15.134082+00:00","updated_at":"2026-07-05T05:34:15.134082+00:00"}