Magnitude-based pruning is one of the simplest methods for pruning neural networks. Despite its simplicity, magnitude-based pruning and its variants demonstrated remarkable performances for pruning modern architectures. Based on the observation that magnitude-based pruning indeed minimizes the Frobenius distortion of a linear operator corresponding to a single layer, we develop a simple pruning method, coined lookahead pruning, by extending the single layer optimization to a multi-layer optimization. Our experimental results demonstrate that the proposed method consistently outperforms magnitude-based pruning on various networks, including VGG and ResNet, particularly in the high-sparsity regime. See https://github.com/alinlab/lookahead_pruning for codes.
@article{arxiv.2002.04809,
title = {Lookahead: A Far-Sighted Alternative of Magnitude-based Pruning},
author = {Sejun Park and Jaeho Lee and Sangwoo Mo and Jinwoo Shin},
journal= {arXiv preprint arXiv:2002.04809},
year = {2020}
}