GNC convolves stochastic gradient noise to smooth sharp minima in large-batch SGD, outperforming isotropic noise for better generalization in distributed deep learning.
On the relation between the sharpest directions of DNN loss and the SGD step length
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD
GNC convolves stochastic gradient noise to smooth sharp minima in large-batch SGD, outperforming isotropic noise for better generalization in distributed deep learning.