most citedAdaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs

2 citations · 2 across the 2 of their papers we have counts for

collaborators

2 papers

math.OC2020

ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization

Xunpeng Huang, Runxin Xu, Hao Zhou +3

Due to its simplicity and outstanding ability to generalize, stochastic gradient descent (SGD) is still the most widely used optimization method despite its slow convergence. Meanw…

math.OC2020★ 2 cited

Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs

Xunpeng Huang, Hao Zhou, Runxin Xu +2

Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency. However their acceleration effect in practice, especially in neu…