Gradient Normalization & Depth Based Decay For Deep Learning
This is an incremental improvement for deep learning practitioners, offering a simple addition to existing optimizers to speed up training.
The paper tackles the problem of training deep neural networks by introducing gradient normalization and depth-based decay, which improved convergence time on DenseNet, ResNet, and LSTM models for image classification and NLP tasks.
In this paper we introduce a novel method of gradient normalization and decay with respect to depth. Our method leverages the simple concept of normalizing all gradients in a deep neural network, and then decaying said gradients with respect to their depth in the network. Our proposed normalization and decay techniques can be used in conjunction with most current state of the art optimizers and are a very simple addition to any network. This method, although simple, showed improvements in convergence time on state of the art networks such as DenseNet and ResNet on image classification tasks, as well as on an LSTM for natural language processing tasks.