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 1702.05142math.OC
收藏

分布式Optimization的精确扩散与学习-II:收敛性分析

Exact Diffusion for Distributed Optimization and Learning --- Part II: Convergence Analysis

Kun Yuan, Bicheng Ying, Xiaochuan Zhao, Ali H. Sayed

摘要:

本文的第一部分[2]开发了精确扩散算法,以消除确定性最优化问题的分布式解决方案所特有的偏差。该算法被证明是适用于一个更大的组合政策比以前的方法在文献中。特别地,组合矩阵不需要是双重随机的,这对图的拓扑结构和通信协议施加了严格的条件。在第二部分中,我们详细研究了精确扩散的收敛性和稳定性,并建立了它的线性收敛速率。我们还表明,它有一个更广泛的稳定范围比额外的共识解决方案,这意味着它是稳定的更广泛的步长,因此,可以达到更快的收敛速度。分析实例和数值模拟说明了理论研究结果。

英文摘要:

Part I of this work [2] developed the exact diffusion algorithm to remove the bias that is characteristic of distributed solutions for deterministic optimization problems. The algorithm was shown to be applicable to a larger set of combination policies than earlier approaches in the literature. In particular, the combination matrices are not required to be doubly stochastic, which impose stringent conditions on the graph topology and communications protocol. In this Part II, we examine the convergence and stability properties of exact diffusion in some detail and establish its linear convergence rate. We also show that it has a wider stability range than the EXTRA consensus solution, meaning that it is stable for a wider range of step-sizes and can, therefore, attain faster convergence rates. Analytical examples and numerical simulations illustrate the theoretical findings.

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。

↑