arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2101.04824cs.LG
收藏

粗量化信号能量有效的分布式学习算法

Energy-Efficient Distributed Learning Algorithms for Coarsely Quantized Signals

CETUC, Pontifical Catholic University of Rio de Janeiro(里约热内卢天主教大学CETUC);University of São Paulo(圣保罗大学)

A. Danaee, R. C. de Lamare, V. H. Nascimento

摘要:

在这项工作中,我们提出了一个节能的分布式学习框架,使用低分辨率ADC和粗量化信号的物联网(IoT)网络。特别是,我们开发了一种分布式量化感知最小均方(DQA-LMS)算法,该算法可以使用用很少的比特量化的信号以节能的方式学习参数,同时需要较低的计算成本。我们还进行了统计分析,建议DQA-LMS算法,包括一个稳定性条件。模拟评估DQA-LMS算法与现有技术的分布式参数估计任务,其中物联网设备以对等模式操作,并证明DQA-LMS算法的有效性。

英文摘要:

In this work, we present an energy-efficient distributed learning framework using low-resolution ADCs and coarsely quantized signals for Internet of Things (IoT) networks. In particular, we develop a distributed quantization-aware least-mean square (DQA-LMS) algorithm that can learn parameters in an energy-efficient fashion using signals quantized with few bits while requiring a low computational cost. We also carry out a statistical analysis of the proposed DQA-LMS algorithm that includes a stability condition. Simulations assess the DQA-LMS algorithm against existing techniques for a distributed parameter estimation task where IoT devices operate in a peer-to-peer mode and demonstrate the effectiveness of the DQA-LMS algorithm.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑