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 1707.08486math.OCcs.NAmath.NA
收藏

凸优化中加速随机化方法的统一框架

Unifying Framework for Accelerated Randomized Methods in Convex Optimization

Pavel Dvurechensky, Alexander Gasnikov, Alexander Tiurin, Vladimir Zholobov

摘要:

本文研究了具有简单约束和不精确预言信息的光滑凸优化问题,预言信息包括目标函数的值、偏导数或方向导数。我们引入了一个统一的框架,它允许构建不同类型的加速随机方法,这样的问题,并证明他们的收敛速度定理。我们专注于加速随机块坐标下降,加速随机方向搜索,加速随机无导数方法,并使用我们的框架,提供他们的版本与不精确的预言信息的问题。我们的贡献还包括加速随机块坐标下降与不精确的预言和熵接近的设置,以及衍生的自由版本的这种方法。此外,我们提出了一个扩展的强凸优化问题的框架。我们还讨论了目标函数的不精确模型的情况下的推广。

英文摘要:

In this paper, we consider smooth convex optimization problems with simple constraints and inexactness in the oracle information such as value, partial or directional derivatives of the objective function. We introduce a unifying framework, which allows to construct different types of accelerated randomized methods for such problems and to prove convergence rate theorems for them. We focus on accelerated random block-coordinate descent, accelerated random directional search, accelerated random derivative-free method and, using our framework, provide their versions for problems with inexact oracle information. Our contribution also includes accelerated random block-coordinate descent with inexact oracle and entropy proximal setup as well as derivative-free version of this method. Moreover, we present an extension of our framework for strongly convex optimization problems. We also discuss an extension for the case of inexact model of the objective function.

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。

↑