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 2201.03930math.OC
收藏

分布式非凸Optimization通信压缩

Communication Compression for Distributed Nonconvex Optimization

Xinlei Yi, Shengjun Zhang, Tao Yang, Tianyou Chai, Karl H. Johansson

摘要:

本文研究了费用函数分布在多个智能体上的分布式非凸优化问题。注意到信息压缩是一个关键的工具,以减少沉重的通信负载的分布式算法代理迭代与邻居进行通信,我们提出了三个分布式原始对偶法压缩通信。前两个算法适用于相对压缩误差有界的一般压缩器类,第三个算法适用于绝对压缩误差有界的一般压缩器类。我们表明,所提出的分布式算法与压缩通信具有可比的收敛性能,最先进的算法与精确的通信。具体地说,我们发现,他们可以找到一阶平稳点的次线性收敛速度$\mathcal{O}(1/T)$时,每个本地的成本函数是光滑的,其中$T$是迭代的总次数,并找到全局最优解的线性收敛速率的一个附加条件下,全球费用函数满足Polyak--Jasiewicz条件。通过数值模拟验证了理论结果的有效性。

英文摘要:

This paper considers distributed nonconvex optimization with the cost functions being distributed over agents. Noting that information compression is a key tool to reduce the heavy communication load for distributed algorithms as agents iteratively communicate with neighbors, we propose three distributed primal--dual algorithms with compressed communication. The first two algorithms are applicable to a general class of compressors with bounded relative compression error and the third algorithm is suitable for two general classes of compressors with bounded absolute compression error. We show that the proposed distributed algorithms with compressed communication have comparable convergence properties as state-of-the-art algorithms with exact communication. Specifically, we show that they can find first-order stationary points with sublinear convergence rate $\mathcal{O}(1/T)$ when each local cost function is smooth, where $T$ is the total number of iterations, and find global optima with linear convergence rate under an additional condition that the global cost function satisfies the Polyak--Łojasiewicz condition. Numerical simulations are provided to illustrate the effectiveness of the theoretical results.

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。

↑