.png){kind=icon}
返回
DNN compression by ADMM-based joint pruning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2021.107988.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The success of deep neural networks (DNNs) has motivated pursuit of both computationally and memory efficient models for applications in resource-constrained systems such as embedded devices. In line with this trend, network pruning methods reducing redundancy in over-parameterized models are being studied actively. Previous works on this research have demonstrated the ability to learn a compact network by imposing sparsity constraints on the parameters, but most of them have difficulty not only in identifying both connections and neurons to be pruned, but also in converging to optimal solutions. We propose a systematic DNN compression method where weights and network architectures are jointly optimized. We solve the joint problem using alternating direction method of multipliers (ADMM), a powerful technique capable of handling non-convex separable program -ming. Additionally, we provide a holistic pruning approach, an integrated form of our method, for automatically pruning networks without specific layer-wise hyper-parameters. To verify our work, we deployed the proposed method to a variety of state-of-the-art convolutional neural networks (CNNs) on three image classification benchmark datasets: MNIST, CIFAR-10, and ImageNet. Results show that the proposed pruning method effectively compresses the network parameters and reduces the computation cost while preserving prediction accuracy. (c) 2021 Elsevier B.V. All rights reserved.
Keyword:
Neural network compression
Structured pruning
Unstructured pruning
Alternative direction method of multipliers (ADMM)
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏Non-convex weighte lp nuclear norm based ADMM framework for image restoration.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Pruning by explaining: A novel criterion for deep neural network pruning解释修剪: 一种新的深度神经网络修剪准则PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容