Fast, Better Training Trick -- Random Gradient

Jiakai Wei

Fast, Better Training Trick -- Random Gradient

Machine Learning 2018-08-22 v1 Machine Learning

Authors: Jiakai Wei

Abstract

In this paper, we will show an unprecedented method to accelerate training and improve performance, which called random gradient (RG). This method can be easier to the training of any model without extra calculation cost, we use Image classification, Semantic segmentation, and GANs to confirm this method can improve speed which is training model in computer vision. The central idea is using the loss multiplied by a random number to random reduce the back-propagation gradient. We can use this method to produce a better result in Pascal VOC, Cifar, Cityscapes datasets.

Keywords

neural network training stochastic gradient descent reinforcement learning

Cite

@article{arxiv.1808.04293,
  title  = {Fast, Better Training Trick -- Random Gradient},
  author = {Jiakai Wei},
  journal= {arXiv preprint arXiv:1808.04293},
  year   = {2018}
}

Comments

arXiv admin note: text overlap with arXiv:1708.07120 by other authors

Related papers

View all related →