论文标题
阶乘力量的力量：（随机）优化的新参数设置
The Power of Factorial Powers: New Parameter settings for (Stochastic) Optimization
论文作者
论文摘要
凸和非凸优化方法的收敛速率取决于选择一系列常数的选择，包括阶梯尺寸，Lyapunov函数常数和动量常数。在这项工作中，我们建议将阶乘力量用作定义融合证明中出现的常数的灵活工具。我们列出了这些序列所享有的许多显着特性，并显示如何将它们应用于收敛证明，以简化或提高动量方法，加速梯度和随机方差降低方法（SVRG）的收敛速率。
The convergence rates for convex and non-convex optimization methods depend on the choice of a host of constants, including step sizes, Lyapunov function constants and momentum constants. In this work we propose the use of factorial powers as a flexible tool for defining constants that appear in convergence proofs. We list a number of remarkable properties that these sequences enjoy, and show how they can be applied to convergence proofs to simplify or improve the convergence rates of the momentum method, accelerated gradient and the stochastic variance reduced method (SVRG).
