We propose an algorithm for decentralized optimization in wireless device-to-device (D2D) networks of pervasive devices such as sensors or 5G handsets, in which the signs of stochastic gradient are used for descent steps. Our algorithm has the convergence rate of O{O} (1/(nT)) in which n{n} is the number of devices and T{T} is the number of learning iterations, saving the communication efficiency by at least 64 times when compared with previous results, and being relatively robust to unexpected errors of adversarial scaling in communication. Theoretical claims are verified by numerical results on a standard benchmark dataset.

中文翻译：

---

设备到设备网络的具有随机梯度符号的分散下降优化


我们提出了一种在传感器或 5G 手机等普及设备的无线设备到设备 (D2D) 网络中进行去中心化优化的算法，其中随机梯度的符号用于下降步骤。我们的算法具有 O{O} (1/(nT)) 的收敛速度，其中 n{n} 是设备数量，T{T} 是学习迭代次数，节省通信效率至少 64 倍与之前的结果相比，并且对于通信中对抗性缩放的意外错误相对稳健。理论主张通过标准基准数据集的数值结果得到验证。