{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IPOHDGXNOX3HBGMZ5URAW3ZN2X","short_pith_number":"pith:IPOHDGXN","schema_version":"1.0","canonical_sha256":"43dc719aed75f6709999ed220b6f2dd5e80ab2b93d88c837bd389ed4e06919ba","source":{"kind":"arxiv","id":"2507.00195","version":1},"attestation_state":"computed","paper":{"title":"What Makes Local Updates Effective: The Role of Data Heterogeneity and Smoothness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kumar Kshitij Patel","submitted_at":"2025-06-30T19:06:02Z","abstract_excerpt":"This thesis contributes to the theoretical understanding of local update algorithms, especially Local SGD, in distributed and federated optimization under realistic models of data heterogeneity. A central focus is on the bounded second-order heterogeneity assumption, which is shown to be both necessary and sufficient for local updates to outperform centralized or mini-batch methods in convex and non-convex settings. The thesis establishes tight upper and lower bounds in several regimes for various local update algorithms and characterizes the min-max complexity of multiple problem classes. At "},"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":"2507.00195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T19:06:02Z","cross_cats_sorted":["cs.AI","cs.MA","math.OC","stat.ML"],"title_canon_sha256":"494b4289858682cecb1a92d052bec145c2113281c4f3a37a22d12b9b52e22e93","abstract_canon_sha256":"44a81fb1829df1335bf68925c8e6b3b954f38cce467e9892652f2c6030dbe716"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:38.958571Z","signature_b64":"WWVZNT0EKAerQmYfraQj/2A4Ppnj7msFEwv6Nisvr0eYhxG/4J7ukN8rt6jF7EtqoRAhZIVgIkobADkhVDYbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43dc719aed75f6709999ed220b6f2dd5e80ab2b93d88c837bd389ed4e06919ba","last_reissued_at":"2026-07-05T11:29:38.958010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:38.958010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Makes Local Updates Effective: The Role of Data Heterogeneity and Smoothness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kumar Kshitij Patel","submitted_at":"2025-06-30T19:06:02Z","abstract_excerpt":"This thesis contributes to the theoretical understanding of local update algorithms, especially Local SGD, in distributed and federated optimization under realistic models of data heterogeneity. A central focus is on the bounded second-order heterogeneity assumption, which is shown to be both necessary and sufficient for local updates to outperform centralized or mini-batch methods in convex and non-convex settings. The thesis establishes tight upper and lower bounds in several regimes for various local update algorithms and characterizes the min-max complexity of multiple problem classes. At "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00195","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/2507.00195/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":"2507.00195","created_at":"2026-07-05T11:29:38.958076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00195v1","created_at":"2026-07-05T11:29:38.958076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00195","created_at":"2026-07-05T11:29:38.958076+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPOHDGXNOX3H","created_at":"2026-07-05T11:29:38.958076+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPOHDGXNOX3HBGMZ","created_at":"2026-07-05T11:29:38.958076+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPOHDGXN","created_at":"2026-07-05T11:29:38.958076+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/IPOHDGXNOX3HBGMZ5URAW3ZN2X","json":"https://pith.science/pith/IPOHDGXNOX3HBGMZ5URAW3ZN2X.json","graph_json":"https://pith.science/api/pith-number/IPOHDGXNOX3HBGMZ5URAW3ZN2X/graph.json","events_json":"https://pith.science/api/pith-number/IPOHDGXNOX3HBGMZ5URAW3ZN2X/events.json","paper":"https://pith.science/paper/IPOHDGXN"},"agent_actions":{"view_html":"https://pith.science/pith/IPOHDGXNOX3HBGMZ5URAW3ZN2X","download_json":"https://pith.science/pith/IPOHDGXNOX3HBGMZ5URAW3ZN2X.json","view_paper":"https://pith.science/paper/IPOHDGXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00195&json=true","fetch_graph":"https://pith.science/api/pith-number/IPOHDGXNOX3HBGMZ5URAW3ZN2X/graph.json","fetch_events":"https://pith.science/api/pith-number/IPOHDGXNOX3HBGMZ5URAW3ZN2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPOHDGXNOX3HBGMZ5URAW3ZN2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPOHDGXNOX3HBGMZ5URAW3ZN2X/action/storage_attestation","attest_author":"https://pith.science/pith/IPOHDGXNOX3HBGMZ5URAW3ZN2X/action/author_attestation","sign_citation":"https://pith.science/pith/IPOHDGXNOX3HBGMZ5URAW3ZN2X/action/citation_signature","submit_replication":"https://pith.science/pith/IPOHDGXNOX3HBGMZ5URAW3ZN2X/action/replication_record"}},"created_at":"2026-07-05T11:29:38.958076+00:00","updated_at":"2026-07-05T11:29:38.958076+00:00"}