Gradient statistics aware power control for over-the-air federated learning in fading channels

N Zhang, M Tao - 2020 IEEE International Conference on …, 2020 - ieeexplore.ieee.org
To enable communication-efficient federated learning, fast model aggregation can be
designed using over-the-air computation (AirComp). In order to implement a reliable and …

Gradient Statistics Aware Power Control for Over-the-Air Federated Learning

N Zhang, M Tao - arXiv preprint arXiv:2003.02089, 2020 - arxiv.org
Federated learning (FL) is a promising technique that enables many edge devices to train a
machine learning model collaboratively in wireless networks. By exploiting the superposition …

Gradient Statistics Aware Power Control for Over-the-Air Federated Learning

N Zhang, M Tao - arXiv e-prints, 2020 - ui.adsabs.harvard.edu
Federated learning (FL) is a promising technique that enables many edge devices to train a
machine learning model collaboratively in wireless networks. By exploiting the superposition …

[PDF][PDF] Gradient Statistics Aware Power Control for Over-the-Air Federated Learning

N Zhang, M Tao - arXiv preprint arXiv:2003.02089, 2020 - researchgate.net
Federated learning (FL) is a promising technique that enables many edge devices to train a
machine learning model collaboratively in wireless networks. By exploiting the superposition …