GoPrune: Accelerated Structured Pruning with $\ell_{2,p}$-Norm Optimization
This work addresses network compression for deployment on resource-constrained edge devices, representing an incremental improvement over existing pruning methods.
The paper tackles the problem of high storage and computational costs in deep convolutional neural networks by proposing GoPrune, an accelerated structured pruning method using an ℓ₂,ₚ-norm optimization, which demonstrates superior performance in compressing ResNet and VGG models on CIFAR datasets.
Convolutional neural networks (CNNs) suffer from rapidly increasing storage and computational costs as their depth grows, which severely hinders their deployment on resource-constrained edge devices. Pruning is a practical approach for network compression, among which structured pruning is the most effective for inference acceleration. Although existing work has applied the $\ell_p$-norm to pruning, it only considers unstructured pruning with $p\in (0, 1)$ and has low computational efficiency. To overcome these limitations, we propose an accelerated structured pruning method called GoPrune. Our method employs the $\ell_{2,p}$-norm for sparse network learning, where the value of $p$ is extended to $[0, 1)$. Moreover, we develop an efficient optimization algorithm based on the proximal alternating minimization (PAM), and the resulting subproblems enjoy closed-form solutions, thus improving compression efficiency. Experiments on the CIFAR datasets using ResNet and VGG models demonstrate the superior performance of the proposed method in network pruning. Our code is available at https://github.com/xianchaoxiu/GoPrune.