Energy-Efficient Distributed Learning With Coarsely Quantized Signals

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. particular, develop a quantization-aware least-mean square (DQA-LMS) algorithm that can learn parameters in fashion with few bits while requiring low computational cost. We also carry out statistical analysis the proposed DQA-LMS includes stability condition. Simulations assess against existing techniques parameter estimation task where IoT devices operate peer-to-peer mode demonstrate effectiveness algorithm.