Variance Suppression: Balanced Training Process in Deep Learning

11/20/2018 ∙ by Tao Yi, et al. ∙ 0

Stochastic gradient descent updates parameters with summation gradient computed from a random data batch. This summation will lead to unbalanced training process if the data we obtained is unbalanced. To address this issue, this paper takes the error variance and error mean both into consideration. The adaptively adjusting approach of two terms trading off is also given in our algorithm. Due to this algorithm can suppress error variance, we named it Variance Suppression Gradient Descent (VSSGD). Experimental results have demonstrated that VSSGD can accelerate the training process, effectively prevent overfitting, improve the networks learning capacity from small samples.



There are no comments yet.


page 6

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.