Structured Data Gradient pruning for Deep Neural Network inference
Accelerating DNN Training with Structured Data Gradient Pruning
Weight pruning is a technique to make deep neural network (dnn) inference more computationally efficient by reducing the number of model parameters over the course of training.However, most weight pruning techniques generally doesnot speed up training and can even require more iterations to reach model convergence.This approach enforces a specific sparsity structure, where only n out of every 4 elements in a matrix can be nonzero, making it amenable to hardwareacceleration.Our approach can achieve a 15-25\% reduction in total training time without significant impact to performance.
