mlsanityData to 14 Oct 2026

Distributed Event-Based Learning via ADMM

arXiv 2405.10618 ↗First posted 17 May 2024cs.LG math.OC stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

We consider a distributed learning problem, where agents minimize a global objective function by exchanging information over a network. Our approach has two distinct features: (i) It substantially reduces communication by triggering communication only when necessary, and (ii) it is agnostic to the data-distribution among the different agents. We therefore guarantee convergence even if the local data-distributions of the agents are arbitrarily distinct. We analyze the convergence rate of the algorithm both in convex and nonconvex settings and derive accelerated convergence rates for the convex case. We also characterize the effect of communication failures and demonstrate that our algorithm is robust to these. The article concludes by presenting numerical results from distributed learning tasks on the MNIST and CIFAR-10 datasets. The experiments underline communication savings of 35% or more due to the event-based communication strategy, show resilience towards heterogeneous data-distributions, and highlight that our approach outperforms common baselines such as FedAvg, FedProx, SCAFFOLD and FedADMM.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 42 of its 65 references that are in the map. First posted on arXiv 17 May 2024.

Builds on

42 of 65 references.

References · 42

  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. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  5. 2018Federated Learning with Non-IID Datacited by 1,108
  6. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  7. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  8. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
  9. 2019Robust Aggregation for Federated Learningcited by 317
  10. 2015A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insightscited by 206
  11. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  12. 2020FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Datacited by 144
30 more
  1. 2018ATOMO: Communication-efficient Learning via Atomic Sparsificationcited by 136
  2. 2013Communication Efficient Distributed Optimization using an Approximate Newton-type Methodcited by 132
  3. 2017Network Topology and Communication-Computation Tradeoffs in Decentralized Optimizationcited by 122
  4. 2016A Variational Perspective on Accelerated Methods in Optimizationcited by 110
  5. 2014Analysis and Design of Optimization Algorithms via Integral Quadratic Constraintscited by 105
  6. 2023Stochastic Controlled Averaging for Federated Learning with Communication Compressioncited by 101
  7. 2018LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learningcited by 96
  8. 2021Decentralized Federated Learning: Balancing Communication and Computing Costscited by 55
  9. 2022Federated Learning via Inexact ADMMcited by 44
  10. 2020Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimizationcited by 43
  11. 2021Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspectivecited by 38
  12. 2022FedADMM: A Federated Primal-Dual Algorithm Allowing Partial Participationcited by 36
  13. 2019A Dynamical Systems Perspective on Nesterov Accelerationcited by 33
  14. 2019GADMM: Fast and Communication Efficient Framework for Distributed Machine Learningcited by 30
  15. 2020Statistically Preconditioned Accelerated Gradient Method for Distributed Optimizationcited by 30
  16. 2021FedDR -- Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimizationcited by 29
  17. 2022FedADMM: A Robust Federated Deep Learning Framework with Adaptivity to System Heterogeneitycited by 25
  18. 2019Feedback Linearization based on Gaussian Processes with event-triggered Online Learningcited by 24
  19. 2015A General Analysis of the Convergence of ADMMcited by 22
  20. 2023Compression with Exact Error Distribution for Federated Learningcited by 11
  21. 2019Event-triggered Learningcited by 9
  22. 2022DADAO: Decoupled Accelerated Decentralized Asynchronous Optimizationcited by 8
  23. 2020Continuous-time Lower Bounds for Gradient-based Algorithmscited by 7
  24. 2022Event-Triggered Time-Varying Bayesian Optimizationcited by 7
  25. 2020Decentralized Learning with Lazy and Approximate Dual Gradientscited by 6
  26. 2024FedADMM-InSa: An Inexact and Self-Adaptive ADMM for Federated Learningcited by 4
  27. 2023A Dynamical Systems Perspective on Discrete Optimizationcited by 3
  28. 2023Federated Learning via Consensus Mechanism on Heterogeneous Data: A New Perspective on Convergencecited by 2
  29. 2023Decentralized ADMM with Compressed and Event-Triggered Communicationcited by 1
  30. 2023Communication-efficient distributed optimization with adaptability to system heterogeneitycited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2024Controlling Participation in Federated Learning with Feedbackcited by 1
  2. 2025A Systems-Theoretic View on the Convergence of Algorithms under Disturbancescited by 0
  3. 2026Co-VLA: Consensus-based Federated Training for Vision-Language-Action Modelscited by 0