mlsanityData to 14 Oct 2026

Provable Reduction in Communication Rounds for Non-Smooth Convex Federated Learning

arXiv 2503.21627 ↗First posted 27 Mar 2025cs.LG math.OCcited by 0

Not on the map. Why?

Abstract (arXiv)

Multiple local steps are key to communication-efficient federated learning. However, theoretical guarantees for such algorithms, without data heterogeneity-bounding assumptions, have been lacking in general non-smooth convex problems. Leveraging projection-efficient optimization methods, we propose FedMLS, a federated learning algorithm with provable improvements from multiple local steps. FedMLS attains an ε-suboptimal solution in O(1/ε) communication rounds, requiring a total of O(1/ε2) stochastic subgradient oracle calls.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 26 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

19 of 26 references.

References · 19

  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. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  5. 2018Federated Learning with Non-IID Datacited by 1,108
  6. 2018Local SGD Converges Fast and Communicates Littlecited by 605
  7. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
  8. 2019Tighter Theory for Local SGD on Identical and Heterogeneous Datacited by 266
  9. 2019On the Convergence of Local Descent Methods in Federated Learningcited by 153
  10. 2020Minibatch vs Local SGD for Heterogeneous Distributed Learningcited by 147
  11. 2022ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!cited by 134
  12. 2020Local SGD: Unified Theory and New Efficient Methodscited by 88
7 more
  1. 2019First Analysis of Local GD on Heterogeneous Datacited by 81
  2. 2021Communication Efficiency in Federated Learning: Achievements and Challengescited by 40
  3. 2022Towards Efficient Communications in Federated Learning: A Contemporary Surveycited by 24
  4. 2022GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexitycited by 18
  5. 2020Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Methodcited by 17
  6. 2024LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compressioncited by 11
  7. 2024FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Modelscited by 5

Built on by

Not cited yet.