{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DKQBDRT5KOSK2WISRNJEW7IN2H","short_pith_number":"pith:DKQBDRT5","schema_version":"1.0","canonical_sha256":"1aa011c67d53a4ad59128b524b7d0dd1def18459614dfc3a74edb384274d8cb7","source":{"kind":"arxiv","id":"2109.02388","version":1},"attestation_state":"computed","paper":{"title":"On Second-order Optimization Methods for Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Martin Jaggi, Sebastian Bischoff, Sebastian U. Stich, Stephan G\\\"unnemann","submitted_at":"2021-09-06T12:04:08Z","abstract_excerpt":"We consider federated learning (FL), where the training data is distributed across a large number of clients. The standard optimization method in this setting is Federated Averaging (FedAvg), which performs multiple local first-order optimization steps between communication rounds. In this work, we evaluate the performance of several second-order distributed methods with local steps in the FL setting which promise to have favorable convergence properties.\n  We (i) show that FedAvg performs surprisingly well against its second-order competitors when evaluated under fair metrics (equal amount 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":"2109.02388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-06T12:04:08Z","cross_cats_sorted":[],"title_canon_sha256":"cdbe8a73da1a8f12a15e8a98e9f8af3eeb09b422a78b486ec9910c8e47b4bd77","abstract_canon_sha256":"824cea23b49e96d01786dec76078bcd9627b59e8253b899b29a53a0d2c88d309"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:41.809240Z","signature_b64":"ArD7O8HVz7t9OQNFJWzRACaJHZKBDxqHfseXOrfn1OAZin3qODBPXAqkts3mg0AxFY63PF3NkZ4yxWsiXOjuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1aa011c67d53a4ad59128b524b7d0dd1def18459614dfc3a74edb384274d8cb7","last_reissued_at":"2026-07-05T03:11:41.808761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:41.808761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Second-order Optimization Methods for Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Martin Jaggi, Sebastian Bischoff, Sebastian U. Stich, Stephan G\\\"unnemann","submitted_at":"2021-09-06T12:04:08Z","abstract_excerpt":"We consider federated learning (FL), where the training data is distributed across a large number of clients. The standard optimization method in this setting is Federated Averaging (FedAvg), which performs multiple local first-order optimization steps between communication rounds. In this work, we evaluate the performance of several second-order distributed methods with local steps in the FL setting which promise to have favorable convergence properties.\n  We (i) show that FedAvg performs surprisingly well against its second-order competitors when evaluated under fair metrics (equal amount of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02388","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/2109.02388/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":"2109.02388","created_at":"2026-07-05T03:11:41.808826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.02388v1","created_at":"2026-07-05T03:11:41.808826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02388","created_at":"2026-07-05T03:11:41.808826+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKQBDRT5KOSK","created_at":"2026-07-05T03:11:41.808826+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKQBDRT5KOSK2WIS","created_at":"2026-07-05T03:11:41.808826+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKQBDRT5","created_at":"2026-07-05T03:11:41.808826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07159","citing_title":"pFedSOP : Accelerating Training Of Personalized Federated Learning Using Second-Order Optimization","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DKQBDRT5KOSK2WISRNJEW7IN2H","json":"https://pith.science/pith/DKQBDRT5KOSK2WISRNJEW7IN2H.json","graph_json":"https://pith.science/api/pith-number/DKQBDRT5KOSK2WISRNJEW7IN2H/graph.json","events_json":"https://pith.science/api/pith-number/DKQBDRT5KOSK2WISRNJEW7IN2H/events.json","paper":"https://pith.science/paper/DKQBDRT5"},"agent_actions":{"view_html":"https://pith.science/pith/DKQBDRT5KOSK2WISRNJEW7IN2H","download_json":"https://pith.science/pith/DKQBDRT5KOSK2WISRNJEW7IN2H.json","view_paper":"https://pith.science/paper/DKQBDRT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.02388&json=true","fetch_graph":"https://pith.science/api/pith-number/DKQBDRT5KOSK2WISRNJEW7IN2H/graph.json","fetch_events":"https://pith.science/api/pith-number/DKQBDRT5KOSK2WISRNJEW7IN2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKQBDRT5KOSK2WISRNJEW7IN2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKQBDRT5KOSK2WISRNJEW7IN2H/action/storage_attestation","attest_author":"https://pith.science/pith/DKQBDRT5KOSK2WISRNJEW7IN2H/action/author_attestation","sign_citation":"https://pith.science/pith/DKQBDRT5KOSK2WISRNJEW7IN2H/action/citation_signature","submit_replication":"https://pith.science/pith/DKQBDRT5KOSK2WISRNJEW7IN2H/action/replication_record"}},"created_at":"2026-07-05T03:11:41.808826+00:00","updated_at":"2026-07-05T03:11:41.808826+00:00"}