{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BL7FECYSY2VBMYFTTNDIW6XDT3","short_pith_number":"pith:BL7FECYS","schema_version":"1.0","canonical_sha256":"0afe520b12c6aa1660b39b468b7ae39eec10201d5c709001e7cf3e4b48ced04f","source":{"kind":"arxiv","id":"1907.02189","version":4},"attestation_state":"computed","paper":{"title":"On the Convergence of FedAvg on Non-IID Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Kaixuan Huang, Shusen Wang, Wenhao Yang, Xiang Li, Zhihua Zhang","submitted_at":"2019-07-04T02:04:56Z","abstract_excerpt":"Federated learning enables a large amount of edge computing devices to jointly learn a model without data sharing. As a leading algorithm in this setting, Federated Averaging (\\texttt{FedAvg}) runs Stochastic Gradient Descent (SGD) in parallel on a small subset of the total devices and averages the sequences only once in a while. Despite its simplicity, it lacks theoretical guarantees under realistic settings. In this paper, we analyze the convergence of \\texttt{FedAvg} on non-iid data and establish a convergence rate of $\\mathcal{O}(\\frac{1}{T})$ for strongly convex and smooth problems, where"},"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":"1907.02189","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-04T02:04:56Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"cea003e2a5970d33b17e4981c7b3ea1025e629d8d85b4f8f03fd7b2c3b66766c","abstract_canon_sha256":"004eb084cc7196fbf311f21e956b20078efca58daec50ec9f9053a0d2f182099"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:23.183897Z","signature_b64":"J72Q74qMFSWsZLpmagvo9yGGJpE9Q7taZJaLFMmBGh3GSNs1V/5ApA2EjecE21M/d7wAXertZRp8MvW/YTYbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0afe520b12c6aa1660b39b468b7ae39eec10201d5c709001e7cf3e4b48ced04f","last_reissued_at":"2026-07-05T01:13:23.183441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:23.183441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Convergence of FedAvg on Non-IID Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Kaixuan Huang, Shusen Wang, Wenhao Yang, Xiang Li, Zhihua Zhang","submitted_at":"2019-07-04T02:04:56Z","abstract_excerpt":"Federated learning enables a large amount of edge computing devices to jointly learn a model without data sharing. As a leading algorithm in this setting, Federated Averaging (\\texttt{FedAvg}) runs Stochastic Gradient Descent (SGD) in parallel on a small subset of the total devices and averages the sequences only once in a while. Despite its simplicity, it lacks theoretical guarantees under realistic settings. In this paper, we analyze the convergence of \\texttt{FedAvg} on non-iid data and establish a convergence rate of $\\mathcal{O}(\\frac{1}{T})$ for strongly convex and smooth problems, where"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02189","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/1907.02189/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":"1907.02189","created_at":"2026-07-05T01:13:23.183503+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.02189v4","created_at":"2026-07-05T01:13:23.183503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02189","created_at":"2026-07-05T01:13:23.183503+00:00"},{"alias_kind":"pith_short_12","alias_value":"BL7FECYSY2VB","created_at":"2026-07-05T01:13:23.183503+00:00"},{"alias_kind":"pith_short_16","alias_value":"BL7FECYSY2VBMYFT","created_at":"2026-07-05T01:13:23.183503+00:00"},{"alias_kind":"pith_short_8","alias_value":"BL7FECYS","created_at":"2026-07-05T01:13:23.183503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06979","citing_title":"Robust Federated Learning Under Real-World Client Churn","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17117","citing_title":"Sensing-Native Over-the-Air Federated Learning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10595","citing_title":"From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10250","citing_title":"Multi-Level Analyzation of Imbalance to Resolve Non-IID-Ness in Federated Learning","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09869","citing_title":"QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01607","citing_title":"FedMTFI: Feature Importance Based Optimized Multi Teacher Knowledge Distillation in Heterogeneous Federated Learning Environment","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27219","citing_title":"Nonlinear Data Integration via Kernel Methods for Data Collaboration Analysis","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30892","citing_title":"Bandwidth Allocation with Device Partitioning for Federated Learning over Industrial IoT networks","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00656","citing_title":"Demystifying the Optimal Fair Classifier in Multi-Class Classification","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2512.09827","citing_title":"Energy-Efficient Federated Learning with Relay-Assisted Aggregation in IIoT Networks","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22898","citing_title":"FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2003.00295","citing_title":"Adaptive Federated Optimization","ref_index":227,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20696","citing_title":"Distributed Direct Preference Optimization","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18656","citing_title":"Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"1909.06335","citing_title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13434","citing_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11857","citing_title":"Beyond Parameter Aggregation: Semantic Consensus for Federated Fine-Tuning of LLMs","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11915","citing_title":"ISAC for AI: A Trade-off Framework Across Data Acquisition and Transfer in Federated Learning","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27434","citing_title":"AdaBFL: Multi-Layer Defensive Adaptive Aggregation for Bzantine-Robust Federated Learning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26388","citing_title":"SplitFT: An Adaptive Federated Split Learning System For LLMs Fine-Tuning","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09144","citing_title":"FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08760","citing_title":"FedGMI: Generative Model-Driven Federated Learning for Probabilistic Mixture Inference","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02337","citing_title":"FedPLT: Scalable, Resource-Efficient, and Heterogeneity-Aware Federated Learning via Partial Layer Training","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06819","citing_title":"Beyond End-to-End: Dynamic Chain Optimization for Private LLM Adaptation on the Edge","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19118","citing_title":"DP-FlogTinyLLM: Differentially private federated log anomaly detection using Tiny LLMs","ref_index":114,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BL7FECYSY2VBMYFTTNDIW6XDT3","json":"https://pith.science/pith/BL7FECYSY2VBMYFTTNDIW6XDT3.json","graph_json":"https://pith.science/api/pith-number/BL7FECYSY2VBMYFTTNDIW6XDT3/graph.json","events_json":"https://pith.science/api/pith-number/BL7FECYSY2VBMYFTTNDIW6XDT3/events.json","paper":"https://pith.science/paper/BL7FECYS"},"agent_actions":{"view_html":"https://pith.science/pith/BL7FECYSY2VBMYFTTNDIW6XDT3","download_json":"https://pith.science/pith/BL7FECYSY2VBMYFTTNDIW6XDT3.json","view_paper":"https://pith.science/paper/BL7FECYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.02189&json=true","fetch_graph":"https://pith.science/api/pith-number/BL7FECYSY2VBMYFTTNDIW6XDT3/graph.json","fetch_events":"https://pith.science/api/pith-number/BL7FECYSY2VBMYFTTNDIW6XDT3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BL7FECYSY2VBMYFTTNDIW6XDT3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BL7FECYSY2VBMYFTTNDIW6XDT3/action/storage_attestation","attest_author":"https://pith.science/pith/BL7FECYSY2VBMYFTTNDIW6XDT3/action/author_attestation","sign_citation":"https://pith.science/pith/BL7FECYSY2VBMYFTTNDIW6XDT3/action/citation_signature","submit_replication":"https://pith.science/pith/BL7FECYSY2VBMYFTTNDIW6XDT3/action/replication_record"}},"created_at":"2026-07-05T01:13:23.183503+00:00","updated_at":"2026-07-05T01:13:23.183503+00:00"}