mlsanityData to 14 Oct 2026

Sharp Gaussian approximations for Decentralized Federated Learning

arXiv 2505.08125 ↗First posted 12 May 2025stat.ML cs.LG math.STcited by 1

Not on the map. Why?

Abstract (arXiv)

Federated Learning has gained traction in privacy-sensitive collaborative environments, with local SGD emerging as a key optimization method in decentralized settings. While its convergence properties are well-studied, asymptotic statistical guarantees beyond convergence remain limited. In this paper, we present two generalized Gaussian approximation results for local SGD and explore their implications. First, we prove a Berry-Esseen theorem for the final local SGD iterates, enabling valid multiplier bootstrap procedures. Second, motivated by robustness considerations, we introduce two distinct time-uniform Gaussian approximations for the entire trajectory of local SGD. The time-uniform approximations support Gaussian bootstrap-based tests for detecting adversarial attacks. Extensive simulations are provided to support our theoretical results.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 43 of its 93 references that are in the map. First posted on arXiv 12 May 2025.

Builds on

43 of 93 references.

References · 43

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,150
  5. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  6. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  7. 2018Local SGD Converges Fast and Communicates Littlecited by 605
  8. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 502
  9. 2020A Unified Theory of Decentralized SGD with Changing Topology and Local Updatescited by 367
  10. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  11. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  12. 2019Asynchronous Federated Optimizationcited by 267
31 more
  1. 2019Tighter Theory for Local SGD on Identical and Heterogeneous Datacited by 266
  2. 2018Don't Use Large Mini-Batches, Use Local SGDcited by 202
  3. 2020Is Local SGD Better than Minibatch SGD?cited by 151
  4. 2020Minibatch vs Local SGD for Heterogeneous Distributed Learningcited by 147
  5. 2017On a Formal Model of Safe and Scalable Self-driving Carscited by 131
  6. 2019Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronizationcited by 107
  7. 2018Blockchained On-Device Federated Learningcited by 106
  8. 2017Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chainscited by 88
  9. 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
  10. 2019Peer-to-peer Federated Learning on Graphscited by 85
  11. 2019Communication-efficient distributed SGD with Sketchingcited by 81
  12. 2016Statistical Inference for Model Parameters in Stochastic Gradient Descentcited by 71
  13. 2021Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspectivecited by 38
  14. 2020Online Covariance Matrix Estimation in Stochastic Gradient Descentcited by 37
  15. 2022Adaptive and Robust Multi-Task Learningcited by 34
  16. 2019Central Server Free Federated Learning over Single-sided Trust Social Networkscited by 33
  17. 2021Optimal and instance-dependent guarantees for Markovian linear stochastic approximationcited by 33
  18. 2019Normal Approximation for Stochastic Gradient Descent via Non-Asymptotic Rates of Martingale CLTcited by 30
  19. 2021Time-uniform central limit theory and asymptotic confidence sequencescited by 29
  20. 2023A Survey on Decentralized Federated Learningcited by 27
  21. 2015Asynchronous stochastic convex optimizationcited by 19
  22. 2024Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learningcited by 19
  23. 2023Online Bootstrap Inference with Nonconvex Stochastic Gradient Descent Estimatorcited by 13
  24. 2025Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descentcited by 10
  25. 2020Communication-efficient Decentralized Local SGD over Undirected Networkscited by 8
  26. 2023Weighted Averaged Stochastic Gradient Descent: Asymptotic Normality and Optimalitycited by 8
  27. 2024Smoothness Adaptive Hypothesis Transfer Learningcited by 8
  28. 2023Multi-Task Learning with Summary Statisticscited by 7
  29. 2023FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networkscited by 7
  30. 2019Computation-Communication Trade-offs and Sensor Selection in Real-time Estimation for Processing Networkscited by 3
  31. 2025Temporal Analysis of Adversarial Attacks in Federated Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Sharp asymptotic theory for Q-learning with LDTZ learning rate and its generalizationcited by 0