无线信道上实现自适应联邦学习，降低通信开销。
Federated learning over physical channels: adaptive algorithms with near-optimal guarantees
- 设计可在物理信道运行的自适应联邦SGD算法
- 理论证明收敛速度随梯度噪声自适应调整
- 适合边缘设备协同训练的低通信场景
在联邦学习中，通过无线物理信道传输信息可显著降低通信成本。本文提出一类新型自适应联邦随机梯度下降（SGD）算法，可在考虑信道噪声和硬件约束的前提下，在物理信道上实施。我们为所提算法建立了理论保证，证明其收敛速率能自适应于随机梯度噪声水平。通过深度学习模型的仿真研究，验证了算法的实际有效性。
原文摘要 · Abstract (English)
In federated learning, communication cost can be significantly reduced by transmitting the information over the air through physical channels. In this paper, we propose a new class of adaptive federated stochastic gradient descent (SGD) algorithms that can be implemented over physical channels, taking into account both channel noise and hardware constraints. We establish theoretical guarantees for the proposed algorithms, demonstrating convergence rates that are adaptive to the stochastic gradient noise level. We also demonstrate the practical effectiveness of our algorithms through simulation studies with deep learning models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。