Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Yifan, Zhang, Cheng, Zhuang, Yuanndon, Dai, Mingzeng, Wang, Haiming, Huang, Yongming
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2410.05354
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912083026640896
author Wang, Yifan
Zhang, Cheng
Zhuang, Yuanndon
Dai, Mingzeng
Wang, Haiming
Huang, Yongming
author_facet Wang, Yifan
Zhang, Cheng
Zhuang, Yuanndon
Dai, Mingzeng
Wang, Haiming
Huang, Yongming
contents Wireless networks supporting artificial intelligence have gained significant attention, with Over-the-Air Federated Learning emerging as a key application due to its unique transmission and distributed computing characteristics. This paper derives error bounds for Over-the-Air Federated Learning in a Cell-free MIMO system and formulates an optimization problem to minimize optimality gap via joint optimization of power control and beamforming. We introduce the MOP-LOFPC algorithm, which employs Lyapunov optimization to decouple long-term constraints across rounds while requiring only causal channel state information. Experimental results demonstrate that MOP-LOFPC achieves a better and more flexible trade-off between the model's training loss and adherence to long-term power constraints compared to existing baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05354
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Over-the-Air Federated Learning in Cell-Free MIMO with Long-term Power Constraint
Wang, Yifan
Zhang, Cheng
Zhuang, Yuanndon
Dai, Mingzeng
Wang, Haiming
Huang, Yongming
Machine Learning
Artificial Intelligence
Wireless networks supporting artificial intelligence have gained significant attention, with Over-the-Air Federated Learning emerging as a key application due to its unique transmission and distributed computing characteristics. This paper derives error bounds for Over-the-Air Federated Learning in a Cell-free MIMO system and formulates an optimization problem to minimize optimality gap via joint optimization of power control and beamforming. We introduce the MOP-LOFPC algorithm, which employs Lyapunov optimization to decouple long-term constraints across rounds while requiring only causal channel state information. Experimental results demonstrate that MOP-LOFPC achieves a better and more flexible trade-off between the model's training loss and adherence to long-term power constraints compared to existing baselines.
title Over-the-Air Federated Learning in Cell-Free MIMO with Long-term Power Constraint
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.05354