arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1607.04818math.OCcs.DC
收藏

非凸Optimization的异步并行算法

Asynchronous Parallel Algorithms for Nonconvex Optimization

Loris Cannelli, Francisco Facchinei, Vyacheslav Kungurtsev, Gesualdo Scutari

摘要:

我们提出了一个新的异步并行块下降算法框架的光滑非凸函数和非光滑凸函数的总和最小化,受到凸和非凸约束。所提出的框架取决于连续凸逼近技术和一种新的概率模型,该模型以比当前最先进的模型更忠实的方式捕获现代计算架构和异步实现的关键要素。该框架的其他关键特征是:i)它以统一的方式涵盖了几种特定的解决方案; ii)它可以容纳各种可能的并行计算架构; iii)它可以处理非凸约束。证明了算法的几乎必然收敛到稳态解,并给出了算法复杂度的理论结果,在工人数目不太大的情况下,算法的线性加速比接近理想.

英文摘要:

We propose a new asynchronous parallel block-descent algorithmic framework for the minimization of the sum of a smooth nonconvex function and a nonsmooth convex one, subject to both convex and nonconvex constraints. The proposed framework hinges on successive convex approximation techniques and a novel probabilistic model that captures key elements of modern computational architectures and asynchronous implementations in a more faithful way than current state-of-the-art models. Other key features of the framework are: i) it covers in a unified way several specific solution methods; ii) it accommodates a variety of possible parallel computing architectures; and iii) it can deal with nonconvex constraints. Almost sure convergence to stationary solutions is proved, and theoretical complexity results are provided, showing nearly ideal linear speedup when the number of workers is not too large.

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。

↑