Accelerated Gradient Descent Learning over Multiple Access Fading Channels

• URL: http://arxiv.org/abs/2107.12452v1
• Date: Mon, 26 Jul 2021 19:51:40 GMT
• Title: Accelerated Gradient Descent Learning over Multiple Access Fading Channels
• Authors: Raz Paul, Yuval Friedman, Kobi Cohen
• Abstract summary: We consider a distributed learning problem in a wireless network, consisting of N distributed edge devices and a parameter server (PS) 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.
• Score: 9.840290491547162
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Robust Federated Learning Over the Air: Combating Heavy-Tailed Noise with Median Anchored Clipping [57.40251549664762]
  We propose a novel gradient clipping method, termed Median Anchored Clipping (MAC), to combat the detrimental effects of heavy-tailed noise. We also derive analytical expressions for the convergence rate of model training with analog over-the-air federated learning under MAC.
  arXiv  Detail & Related papers  (2024-09-23T15:11:40Z)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Blind Federated Learning via Over-the-Air q-QAM [11.956183457374186]
  We investigate edge learning over a fading multiple federated channel. We introduce a pioneering digital-the-air modulation over the federated uplink-the-air channel. We find that the number of antennas at the edge server and adopting higher-order modulations improve the accuracy up to 60%.
  arXiv  Detail & Related papers  (2023-11-07T12:02:59Z)
• Over-the-Air Federated Learning and Optimization [52.5188988624998]
  We focus on Federated learning (FL) via edge-the-air computation (AirComp) We describe the convergence of AirComp-based FedAvg (AirFedAvg) algorithms under both convex and non- convex settings. For different types of local updates that can be transmitted by edge devices (i.e., model, gradient, model difference), we reveal that transmitting in AirFedAvg may cause an aggregation error. In addition, we consider more practical signal processing schemes to improve the communication efficiency and extend the convergence analysis to different forms of model aggregation error caused by these signal processing schemes.
  arXiv  Detail & Related papers  (2023-10-16T05:49:28Z)
• Optimization Guarantees of Unfolded ISTA and ADMM Networks With Smooth Soft-Thresholding [57.71603937699949]
  We study optimization guarantees, i.e., achieving near-zero training loss with the increase in the number of learning epochs. We show that the threshold on the number of training samples increases with the increase in the network width.
  arXiv  Detail & Related papers  (2023-09-12T13:03:47Z)
• Communication-Efficient Federated Learning via Quantized Compressed Sensing [82.10695943017907]
  The presented framework consists of gradient compression for wireless devices and gradient reconstruction for a parameter server. Thanks to gradient sparsification and quantization, our strategy can achieve a higher compression ratio than one-bit gradient compression. We demonstrate that the framework achieves almost identical performance with the case that performs no compression.
  arXiv  Detail & Related papers  (2021-11-30T02:13:54Z)
• Wireless Federated Learning with Limited Communication and Differential Privacy [21.328507360172203]
  This paper investigates the role of dimensionality reduction in efficient communication and differential privacy (DP) of the local datasets at the remote users for over-the-air computation (AirComp)-based federated learning (FL) model.
  arXiv  Detail & Related papers  (2021-06-01T15:23:12Z)
• Bayesian Federated Learning over Wireless Networks [87.37301441859925]
  Federated learning is a privacy-preserving and distributed training method using heterogeneous data sets stored at local devices. This paper presents an efficient modified BFL algorithm called scalableBFL (SBFL)
  arXiv  Detail & Related papers  (2020-12-31T07:32:44Z)
• Fast Convergence Algorithm for Analog Federated Learning [30.399830943617772]
  We propose an AirComp-based FedSplit algorithm for efficient analog federated learning over wireless channels. We prove that the proposed algorithm linearly converges to the optimal solutions under the assumption that the objective function is strongly convex and smooth. Our algorithm is theoretically and experimentally verified to be much more robust to the ill-conditioned problems with faster convergence compared with other benchmark FL algorithms.
  arXiv  Detail & Related papers  (2020-10-30T10:59:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.