Robustness Analysis of Non-Convex Stochastic
Gradient Descent using Biased Expectations
Kevin Scaman Cédric Malherbe
Huawei Noah’s Ark Lab
Abstract
This work proposes a novel analysis of stochastic gradient descent (SGD) for
non-convex and smooth optimization. Our analysis sheds light on the impact of the
probability distribution of the gradient noise on the convergence rate of the norm
of the gradient. In the ...


雷达卡



京公网安备 11010802022788号







