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 1906.07392math.OC
收藏

并行随机块坐标前后向算法:统一收敛性分析

Parallel Random Block-Coordinate Forward-Backward Algorithm: A Unified Convergence Analysis

Saverio Salzo, Silvia Villa

摘要:

我们研究了块坐标的前向-后向算法,在该算法中,块以随机和可能并行的方式更新,根据任意的概率。该算法允许沿块坐标的不同步长,以充分利用目标函数的平滑特性。在凸情形和无穷维情形下,我们建立了迭代的几乎必然弱收敛性和函数值均值的渐近速度o(1/n).在强凸性和误差界条件下,我们得到了线性速率.我们的分析是基于一个抽象的随机下降算法,它允许扩展和简化现有的结果收敛原理。

英文摘要:

We study the block-coordinate forward-backward algorithm in which the blocks are updated in a random and possibly parallel manner, according to arbitrary probabilities. The algorithm allows different stepsizes along the block-coordinates to fully exploit the smoothness properties of the objective function. In the convex case and in an infinite dimensional setting, we establish almost sure weak convergence of the iterates and the asymptotic rate o(1/n) for the mean of the function values. We derive linear rates under strong convexity and error bound conditions. Our analysis is based on an abstract convergence principle for stochastic descent algorithms which allows to extend and simplify existing 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。

↑