Energy-Efficient Distributed Learning Algorithms for Coarsely Quantized Signals
This work addresses energy efficiency for IoT devices in distributed learning, but it appears incremental as it builds on existing quantization-aware methods.
The paper tackled the problem of energy-efficient distributed learning in IoT networks by developing a distributed quantization-aware least-mean square (DQA-LMS) algorithm that uses coarsely quantized signals, resulting in effective parameter estimation with low computational cost as demonstrated in simulations.
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.