arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1711.03439math.OCstat.ML
收藏

非光滑凸优化的光滑原始-对偶坐标下降算法

Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex Optimization

Ahmet Alacaoglu, Quoc Tran-Dinh, Olivier Fercoq, Volkan Cevher

摘要:

提出了一种新的适用于凸优化模板的随机坐标下降法。我们的分析依赖于一个新的组合的四个想法适用于原始-对偶间隙函数:平滑,加速,同伦和坐标下降与非均匀采样。因此,我们的方法具有第一个收敛速度保证之间的坐标下降法,这是最有名的各种常见的结构假设下的模板。我们提供了数值证据来支持的理论结果与国家的最先进的算法进行比较。

英文摘要:

We propose a new randomized coordinate descent method for a convex optimization template with broad applications. Our analysis relies on a novel combination of four ideas applied to the primal-dual gap function: smoothing, acceleration, homotopy, and coordinate descent with non-uniform sampling. As a result, our method features the first convergence rate guarantees among the coordinate descent methods, that are the best-known under a variety of common structure assumptions on the template. We provide numerical evidence to support the theoretical results with a comparison to state-of-the-art algorithms.

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。

↑