{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LWBP2ZUTCHKMTQPXXE776I3UMA","short_pith_number":"pith:LWBP2ZUT","schema_version":"1.0","canonical_sha256":"5d82fd669311d4c9c1f7b93fff23746002df83fc75c20ad1cb1087c26529de7e","source":{"kind":"arxiv","id":"2412.02781","version":3},"attestation_state":"computed","paper":{"title":"Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Eduard Gorbunov, Grigory Malinovsky, Martin Tak\\'a\\v{c}, Peter Richt\\'arik, Petr Ostroukhov, Samuel Horv\\'ath, Yury Demidovich","submitted_at":"2024-12-03T19:20:56Z","abstract_excerpt":"Non-convex Machine Learning problems typically do not adhere to the standard smoothness assumption. Based on empirical findings, Zhang et al. (2020b) proposed a more realistic generalized $(L_0, L_1)$-smoothness assumption, though it remains largely unexplored. Many existing algorithms designed for standard smooth problems need to be revised. However, in the context of Federated Learning, only a few works address this problem but rely on additional limiting assumptions. In this paper, we address this gap in the literature: we propose and analyze new methods with local steps, partial participat"},"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":"2412.02781","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-12-03T19:20:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c91b07eece05010d6df9d84fbceb617691d401efaee777bee0dba08130b5819d","abstract_canon_sha256":"5f03299bb322ad339341c12845adf1aa9dd817f13172a8ec6b8e4967bddf6f44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:34.225905Z","signature_b64":"UYXtAEnDEu+YOmZXuo67ZDRIskUyHRze9yIXcKUaVdEf5XxnD6yrfSLxBK82tep98/qm9qjOrLUJsrrh/uapDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d82fd669311d4c9c1f7b93fff23746002df83fc75c20ad1cb1087c26529de7e","last_reissued_at":"2026-07-05T10:47:34.225421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:34.225421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Eduard Gorbunov, Grigory Malinovsky, Martin Tak\\'a\\v{c}, Peter Richt\\'arik, Petr Ostroukhov, Samuel Horv\\'ath, Yury Demidovich","submitted_at":"2024-12-03T19:20:56Z","abstract_excerpt":"Non-convex Machine Learning problems typically do not adhere to the standard smoothness assumption. Based on empirical findings, Zhang et al. (2020b) proposed a more realistic generalized $(L_0, L_1)$-smoothness assumption, though it remains largely unexplored. Many existing algorithms designed for standard smooth problems need to be revised. However, in the context of Federated Learning, only a few works address this problem but rely on additional limiting assumptions. In this paper, we address this gap in the literature: we propose and analyze new methods with local steps, partial participat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02781","kind":"arxiv","version":3},"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/2412.02781/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":"2412.02781","created_at":"2026-07-05T10:47:34.225479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02781v3","created_at":"2026-07-05T10:47:34.225479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02781","created_at":"2026-07-05T10:47:34.225479+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWBP2ZUTCHKM","created_at":"2026-07-05T10:47:34.225479+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWBP2ZUTCHKMTQPX","created_at":"2026-07-05T10:47:34.225479+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWBP2ZUT","created_at":"2026-07-05T10:47:34.225479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.06563","citing_title":"Theoretical Foundations of Communication-Efficient, Robust, and Practical Distributed and Federated Optimization","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWBP2ZUTCHKMTQPXXE776I3UMA","json":"https://pith.science/pith/LWBP2ZUTCHKMTQPXXE776I3UMA.json","graph_json":"https://pith.science/api/pith-number/LWBP2ZUTCHKMTQPXXE776I3UMA/graph.json","events_json":"https://pith.science/api/pith-number/LWBP2ZUTCHKMTQPXXE776I3UMA/events.json","paper":"https://pith.science/paper/LWBP2ZUT"},"agent_actions":{"view_html":"https://pith.science/pith/LWBP2ZUTCHKMTQPXXE776I3UMA","download_json":"https://pith.science/pith/LWBP2ZUTCHKMTQPXXE776I3UMA.json","view_paper":"https://pith.science/paper/LWBP2ZUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02781&json=true","fetch_graph":"https://pith.science/api/pith-number/LWBP2ZUTCHKMTQPXXE776I3UMA/graph.json","fetch_events":"https://pith.science/api/pith-number/LWBP2ZUTCHKMTQPXXE776I3UMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWBP2ZUTCHKMTQPXXE776I3UMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWBP2ZUTCHKMTQPXXE776I3UMA/action/storage_attestation","attest_author":"https://pith.science/pith/LWBP2ZUTCHKMTQPXXE776I3UMA/action/author_attestation","sign_citation":"https://pith.science/pith/LWBP2ZUTCHKMTQPXXE776I3UMA/action/citation_signature","submit_replication":"https://pith.science/pith/LWBP2ZUTCHKMTQPXXE776I3UMA/action/replication_record"}},"created_at":"2026-07-05T10:47:34.225479+00:00","updated_at":"2026-07-05T10:47:34.225479+00:00"}