BriefGPT.xyz
Dec, 2020
通过渐进正则化进行神经剪枝
Neural Pruning via Growing Regularization
HTML
PDF
Huan Wang, Can Qin, Yulun Zhang, Yun Fu
TL;DR
本文提出了一种新的方法,将正则化引入到神经网络的剪枝问题中,并提出了一种增量L2规范化变量的方法来解决剪枝安排和权重重要性评分的问题。这种增量非常成功,使得我们的算法在结构化和非结构化的剪枝条件下都具有可扩展性,并在CIFAR和ImageNet数据集上取得了与许多现有算法相媲美的结果。
Abstract
regularization
has long been utilized to learn sparsity in
deep neural network pruning
. However, its role is mainly explored in the small penalty strength regime. In this work, we extend its application to a new
→