arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.08822math.OC
收藏

结构复合材料问题的Bregman距离随机方差缩减算法

A Stochastic Variance Reduction Algorithm with Bregman Distances for Structured Composite Problems

Nguyen Van Dung, Băng Công Vũ

摘要:

本文提出了一种新的带Bregman距离的随机原始对偶分裂方法,用于求解非欧几里得空间中包含下确值卷积的结构复合问题.在一般情况下,在较弱的步长条件下,证明了原对偶间隙的期望次线性收敛性。在Bregman函数的强凸性等附加条件下,得到了算法的线性收敛速率.

英文摘要:

We develop a novel stochastic primal dual splitting method with Bregman distances for solving a structured composite problems involving infimal convolutions in non-Euclidean spaces. The sublinear convergence in expectation of the primal-dual gap is proved under mild conditions on stepsize for the general case. The linear convergence rate is obtained under additional condition like the strong convexity relative to Bregman functions.

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。

↑