当前位置: X-MOL 学术IEEE Trans. Signal Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Blind Over-the-Air Computation and Data Fusion via Provable Wirtinger Flow
IEEE Transactions on Signal Processing ( IF 5.4 ) Pub Date : 2020-01-01 , DOI: 10.1109/tsp.2020.2970338
Jialin Dong , Yuanming Shi , Zhi Ding

Over-the-air computation (AirComp) shows great promise to support fast data fusion in Internet-of-Things (IoT) networks. AirComp typically computes desired functions of distributed sensing data by exploiting superposed data transmission in multiple access channels. To overcome its reliance on channel state information (CSI), this work proposes a novel blind over-the-air computation (BlairComp) without requiring CSI access, particularly for low complexity and low latency IoT networks. To solve the resulting non-convex optimization problem without the initialization dependency exhibited by the solutions of a number of recently proposed efficient algorithms, we develop a Wirtinger flow solution to the BlairComp problem based on random initialization. We establish the global convergence guarantee of Wirtinger flow with random initialization for BlairComp problem, which enjoys a model-agnostic and natural initialization implementation for practitioners with theoretical guarantees. Specifically, in the first stage of the algorithm, the iteration of randomly initialized Wirtinger flow given sufficient data samples can enter a local region that enjoys strong convexity and strong smoothness within a few iterations. We also prove the estimation error of BlairComp in the local region to be sufficiently small. We show that, at the second stage of the algorithm, its estimation error decays exponentially at a linear convergence rate.

中文翻译:

通过可证明的 Wirtinger Flow 进行盲传计算和数据融合

空中计算 (AirComp) 显示出支持物联网 (IoT) 网络中快速数据融合的巨大希望。AirComp 通常通过利用多接入信道中的叠加数据传输来计算分布式传感数据的所需函数。为了克服对信道状态信息 (CSI) 的依赖,这项工作提出了一种无需 CSI 访问的新型盲空中计算 (BlairComp),特别是对于低复杂性和低延迟的物联网网络。为了解决由此产生的非凸优化问题,而没有最近提出的许多有效算法的解决方案所表现出的初始化依赖性,我们开发了基于随机初始化的 BlairComp 问题的 Wirtinger 流解决方案。我们为BlairComp问题建立了具有随机初始化的Wirtinger流的全局收敛保证,对于具有理论保证的从业者来说,它享有与模型无关且自然的初始化实现。具体来说,在算法的第一阶段,随机初始化的 Wirtinger 流在给定足够的数据样本的情况下,在几次迭代中就可以进入一个具有强凸性和强平滑性的局部区域。我们还证明了 BlairComp 在局部区域的估计误差足够小。我们表明,在算法的第二阶段,其估计误差以线性收敛速度呈指数衰减。在算法的第一阶段,随机初始化的 Wirtinger 流的迭代在给定足够的数据样本的情况下可以在几次迭代内进入一个具有强凸性和强平滑性的局部区域。我们还证明了 BlairComp 在局部区域的估计误差足够小。我们表明,在算法的第二阶段,其估计误差以线性收敛速度呈指数衰减。在算法的第一阶段,随机初始化的 Wirtinger 流的迭代在给定足够的数据样本的情况下,可以在几次迭代内进入一个具有强凸性和强平滑性的局部区域。我们还证明了 BlairComp 在局部区域的估计误差足够小。我们表明,在算法的第二阶段,其估计误差以线性收敛速度呈指数衰减。
更新日期:2020-01-01
down
wechat
bug