BriefGPT.xyz
Feb, 2020
关于Nesterov加速梯度方法在随机设置下的收敛性
On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings
HTML
PDF
Mahmoud Assran, Michael Rabbat
TL;DR
研究了Nesterov加速梯度方法在随机逼近和有限和设置下的表现，发现使用通常的步长和动量参数，该方法在后者可能发散，进而阐明了这种方法在此情况下可能失败的原因。
Abstract
We study
nesterov's accelerated gradient method
in the
stochastic approximation setting
(unbiased gradients with bounded variance) and the
finite
→