activity
20152024
most citedBypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification

15 citations · 37 across the 10 of their papers we have counts for

collaborators
Showing 2019Show all

1 paper · 1 filter

cs.LG2019★ 6 cited

Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization

Xinyan Li, Qilong Gu, Yingxue Zhou +2

While stochastic gradient descent (SGD) and variants have been surprisingly successful for training deep nets, several aspects of the optimization dynamics and generalization are s…