mlsanityData to 7 Oct 2026

Accelerated Gradient Descent Learning over Multiple Access Fading Channels

arXiv 2107.12452 ↗First posted 26 Jul 2021cs.LG eess.SPcited by 14

Not on the map. Why?

Abstract (arXiv)

We consider a distributed learning problem in a wireless network, consisting of N distributed edge devices and a parameter server (PS). The objective function is a sum of the edge devices' local loss functions, who aim to train a shared model by communicating with the PS over multiple access channels (MAC). This problem has attracted a growing interest in distributed sensing systems, and more recently in federated learning, known as over-the-air computation. In this paper, we develop a novel Accelerated Gradient-descent Multiple Access (AGMA) algorithm that uses momentum-based gradient signals over noisy fading MAC to improve the convergence rate as compared to existing methods. Furthermore, AGMA does not require power control or beamforming to cancel the fading effect, which simplifies the implementation complexity. We analyze AGMA theoretically, and establish a finite-sample bound of the error for both convex and strongly convex loss functions with Lipschitz gradient. For the strongly convex case, we show that AGMA approaches the best-known linear convergence rate as the network increases. For the convex case, we show that AGMA significantly improves the sub-linear convergence rate as compared to existing methods. Finally, we present simulation results using real datasets that demonstrate better performance by AGMA.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 19 of its 58 references that are in the map. First posted on arXiv 26 Jul 2021.

Builds on

19 of 58 references.

References · 19

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  3. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 262
  4. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
  5. 2019Federated Learning over Wireless Fading Channelscited by 178
  6. 2019Hierarchical Federated Learning Across Heterogeneous Cellular Networkscited by 98
  7. 2018LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learningcited by 95
  8. 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 72
  9. 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 61
  10. 2020Wireless Federated Learning with Local Differential Privacycited by 50
  11. 2021Federated Learning: A Signal Processing Perspectivecited by 49
  12. 2019Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Datacited by 39
7 more
  1. 2019Energy-Efficient Radio Resource Allocation for Federated Edge Learningcited by 39
  2. 2020Scheduled Restart Momentum for Accelerated Stochastic Gradient Descentcited by 24
  3. 2019Energy-Aware Analog Aggregation for Federated Learning with Redundant Datacited by 23
  4. 2020Communication Efficient Federated Learning over Multiple Access Channelscited by 11
  5. 2019Collaborative Machine Learning at the Wireless Edge with Blind Transmitterscited by 9
  6. 2020Optimizing Over-the-Air Computation in IRS-Aided C-RAN Systemscited by 5
  7. 2020Distributed Sparse SGD with Majority Votingcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 7; 2024: 4; 2025: 1.

14 papers.

Sort:

  1. 2022Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learningcited by 59
  2. 2022A Survey on Over-the-Air Computationcited by 19
  3. 2023Over-the-Air Federated Learning and Optimizationcited by 10
  4. 2023Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approachcited by 8
  5. 2024Federated Learning via Lattice Joint Source-Channel Codingcited by 6
  6. 2024Compute-Update Federated Learning: A Lattice Coding Approach Over-the-Aircited by 5
  7. 2024Over-the-Air Federated Learning via Weighted Aggregationcited by 5
  8. 2023AirFL-Mem: Improving Communication-Learning Trade-Off by Long-Term Memorycited by 4
  9. 2024Adaptive Federated Learning Over the Aircited by 4
  10. 2025Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processingcited by 3
  11. 2023Sparse Training for Federated Learning with Regularized Error Correctioncited by 2
  12. 2023Accelerating Wireless Federated Learning via Nesterov's Momentum and Distributed Principle Component Analysiscited by 1
2 more
  1. 2023PolarAir: A Compressed Sensing Scheme for Over-the-Air Federated Learningcited by 0
  2. 2023A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systemscited by 0