# Fast, Better Training Trick -- Random Gradient

arXiv: https://arxiv.org/abs/1808.04293 · HTML: https://mlsanity.com/paper/1808.04293/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2018.

## Built on by (most cited first, 1 of 1)

- [Highlighting the Importance of Reducing Research Bias and Carbon Emissions in CNNs](https://mlsanity.com/paper/2106.03242/) (2021)

## Abstract (arXiv)

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.