BriefGPT.xyz
Oct, 2019
统一镜像下降和对偶平均
Unifying mirror descent and dual averaging
HTML
PDF
Anatoli Juditsky, Joon Kwon, Éric Moulines
TL;DR
本文介绍并分析了一族新的一阶优化算法,它对镜像下降和对偶平均进行了推广和统一,并定义了新的约束优化算法,结合了镜像下降和对偶平均的优点。我们的初步模拟研究表明,在某些情况下,这些新算法显著优于现有方法。
Abstract
We introduce and analyse a new family of algorithms which generalizes and unifies both the
mirror descent
and the
dual averaging
algorithms. The unified analysis of the algorithms involves the introduction of a g
→