arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.07366math.OC
收藏

加速梯度法的因子- $\sqrt{2}$加速

Factor-$\sqrt{2}$ Acceleration of Accelerated Gradient Methods

Chanwoo Park, Jisun Park, Ernest K. Ryu

摘要:

优化梯度法(OGM)提供了一个因素- $\sqrt{2}$加速Nesterov的著名加速梯度法在凸(但非强凸)设置。然而,这种改进的加速机制尚未得到很好的理解; OGM的先前分析依赖于计算机辅助证明方法,因此尽管可以验证和正确,但对人类来说是不透明的。在这项工作中,我们提出了一个新的分析OGM的基础上的李雅普诺夫函数和线性耦合。这些分析是在没有计算机帮助的情况下开发和呈现的,并且是人类可以理解的。此外,我们推广OGM的加速机制,并获得一个因素- $\sqrt{2}$加速比在其他设置:加速与一个简单的合理的步长,强凸设置,和镜像下降设置。

英文摘要:

The optimized gradient method (OGM) provides a factor-$\sqrt{2}$ speedup upon Nesterov's celebrated accelerated gradient method in the convex (but non-strongly convex) setup. However, this improved acceleration mechanism has not been well understood; prior analyses of OGM relied on a computer-assisted proof methodology, so the proofs were opaque for humans despite being verifiable and correct. In this work, we present a new analysis of OGM based on a Lyapunov function and linear coupling. These analyses are developed and presented without the assistance of computers and are understandable by humans. Furthermore, we generalize OGM's acceleration mechanism and obtain a factor-$\sqrt{2}$ speedup in other setups: acceleration with a simpler rational stepsize, the strongly convex setup, and the mirror descent setup.

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。

↑