Exploring the Effect of ℓ0 /ℓ2 Regularization in Neural Network Pruning using the LC Toolkit
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2022)
摘要
The LC Toolkit is an open-source library written in Python and PyTorch that allows to compress any neural network using several compressions including quantization, pruning, and low-rank. The versatility of the framework is rooted in the principled mathematical formulation of the underlying network compression problems with subsequent optimization by learning-compression (LC) algorithm. In this paper, we utilize the LC toolkit’s common algorithmic base to take a deeper look into ℓ
0
-constrained pruning problems defined as follows: given a budget of κ non-zero weights, which weights should be pruned in the final network? We observe that ℓ
0
-pruned networks have a different connectivity structure compared to pruning results using ℓ
1
norm. We propose a change to the formulation of the problem involving a small amount of ℓ
2
weight decay which has a favorable effect on connectivity structure. We study the properties of the proposed ℓ
0
+ ℓ
2
formulation using the LC toolkit and empirically demonstrate that such a scheme achieves a competitive sparsity-error tradeoff while having better structural sparsity.
更多查看译文
关键词
neural network compression toolkits,weight pruning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要