mlsanityData to 14 Oct 2026

Convergence Analysis of Over-the-Air FL with Compression and Power Control via Clipping

arXiv 2305.11135 ↗First posted 18 May 2023cs.IT cs.LG eess.SPcited by 2

Not on the map. Why?

Abstract (arXiv)

One of the key challenges towards the deployment of over-the-air federated learning (AirFL) is the design of mechanisms that can comply with the power and bandwidth constraints of the shared channel, while causing minimum deterioration to the learning performance as compared to baseline noiseless implementations. For additive white Gaussian noise (AWGN) channels with instantaneous per-device power constraints, prior work has demonstrated the optimality of a power control mechanism based on norm clipping. This was done through the minimization of an upper bound on the optimality gap for smooth learning objectives satisfying the Polyak-Lojasiewicz (PL) condition. In this paper, we make two contributions to the development of AirFL based on norm clipping, which we refer to as AirFL-Clip. First, we provide a convergence bound for AirFLClip that applies to general smooth and non-convex learning objectives. Unlike existing results, the derived bound is free from run-specific parameters, thus supporting an offline evaluation. Second, we extend AirFL-Clip to include Top-k sparsification and linear compression. For this generalized protocol, referred to as AirFL-Clip-Comp, we derive a convergence bound for general smooth and non-convex learning objectives. We argue, and demonstrate via experiments, that the only time-varying quantities present in the bound can be efficiently estimated offline by leveraging the well-studied properties of sparse recovery algorithms.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 13 of its 18 references that are in the map. First posted on arXiv 18 May 2023.

Builds on

13 of 18 references.

References · 13

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2020Adaptive Federated Optimizationcited by 1,046
  3. 2018Federated Learning via Over-the-Air Computationcited by 219
  4. 2019Federated Learning over Wireless Fading Channelscited by 183
  5. 2019Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computationscited by 181
  6. 2020One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysiscited by 112
  7. 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 73
  8. 2020Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Controlcited by 63
  9. 2021Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysiscited by 51
  10. 2021Optimized Power Control Design for Over-the-Air Federated Edge Learningcited by 48
  11. 2020Decentralized Federated Learning via SGD over Wireless D2D Networkscited by 33
  12. 2021Wireless Federated Langevin Monte Carlo: Repurposing Channel Noise for Bayesian Sampling and Privacycited by 10
1 more
  1. 2022Communication-Efficient Federated Learning over MIMO Multiple Access Channelscited by 4

Built on by

Cited by year

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

2 papers.

  1. 2024Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offscited by 3
  2. 2025Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Stationcited by 1