English

Lookahead: A Far-Sighted Alternative of Magnitude-based Pruning

Machine Learning 2020-02-17 v1 Machine Learning

Abstract

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.

Keywords

Cite

@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}
}

Comments

ICLR 2020, camera ready

R2 v1 2026-06-23T13:39:10.826Z