Communication compression techniques are of growing interests in studying the decentralized optimization problem under limited communication, where the global objective is to minimize the average of local cost functions over networked agents using only local computation and peer-to-peer communication. In this paper, we propose a novel compressed gradient tracking algorithm (C-GT) that combines gradient tracking technique with communication compression. We show that C-GT inherits the advantages of gradient tracking-based algorithms, and in particular, achieves linear convergence rate for strongly convex and smooth objective functions. Numerical examples further demonstrate the efficiency and flexibility of the proposed algorithm.

翻译：通信压缩技术对于在有限通信条件下研究分散化优化问题的兴趣日益浓厚,全球目标是仅利用本地计算和同行通信,将网络化代理商的当地成本功能的平均值降至最低;在本文件中,我们提议采用新的压缩梯度跟踪算法(C-GT),将梯度跟踪技术与通信压缩相结合;我们表明,C-GT继承了梯度跟踪算法的优势,特别是为强电流和平稳客观功能实现了线性趋同率。 数字实例进一步证明了拟议算法的效率和灵活性。