Non-Gaussianity of Stochastic Gradient Noise

What enables Stochastic Gradient Descent (SGD) to achieve better generalization than Gradient Descent (GD) in Neural Network training? This question has attracted much attention. In this paper, we study the distribution of the Stochastic Gradient Noise (SGN) vectors during the training. We observe that for batch sizes \(256\) and above, the distribution is best described as Gaussian at-least in the early phases of training. This holds across data-sets, architectures, and other choices.

The paper has been accepted at the SEDL workshop at NeurIPS 2019.

Please find the below resources:

1. ArXiv.