mlsanityData to 14 Oct 2026

Federated learning over physical channels: adaptive algorithms with near-optimal guarantees

arXiv 2509.02538 ↗First posted 2 Sep 2025cs.LG cs.IT eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

In federated learning, communication cost can be significantly reduced by transmitting the information over the air through physical channels. In this paper, we propose a new class of adaptive federated stochastic gradient descent (SGD) algorithms that can be implemented over physical channels, taking into account both channel noise and hardware constraints. We establish theoretical guarantees for the proposed algorithms, demonstrating convergence rates that are adaptive to the stochastic gradient noise level. We also demonstrate the practical effectiveness of our algorithms through simulation studies with deep learning models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 36 references that are in the map. First posted on arXiv 2 Sep 2025.

Builds on

19 of 36 references.

References · 19

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  3. 2018Local SGD Converges Fast and Communicates Littlecited by 605
  4. 2015Deep Learning with Limited Numerical Precisioncited by 376
  5. 2018Federated Learning via Over-the-Air Computationcited by 219
  6. 2019Federated Learning over Wireless Fading Channelscited by 183
  7. 2015Communication Complexity of Distributed Convex Learning and Optimizationcited by 60
  8. 2020Federated Learning With Quantized Global Model Updatescited by 55
  9. 2017Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networkscited by 44
  10. 2017Artificial Intelligence and Statisticscited by 43
  11. 2019Robust Federated Learning with Noisy Communicationcited by 34
  12. 2020Convergence of Federated Learning over a Noisy Downlinkcited by 29
7 more
  1. 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directionscited by 21
  2. 2022Joint Device Selection and Power Control for Wireless Federated Learningcited by 20
  3. 2023Randomized Quantization is All You Need for Differential Privacy in Federated Learningcited by 17
  4. 2023Accelerated stochastic approximation with state-dependent noisecited by 11
  5. 2022Over-the-Air Federated Learning with Joint Adaptive Computation and Power Controlcited by 9
  6. 2023Communication Efficient Private Federated Learning Using Ditheringcited by 9
  7. 2024Robust Federated Learning Over the Air: Combating Heavy-Tailed Noise with Median Anchored Clippingcited by 3

Built on by

Not cited yet.