Pruning Neural Networks with Velocity-Constrained Optimization

Abstract

Pruning has gained prominence as a way to compress over-parameterized neural networks. While pruning can be understood as solving a sparsity-constrained optimization problem, pruning by di- rectly solving this problem has been relatively underexplored. In this paper, we propose a method to prune neural networks using the MJ algorithm, which interprets constrained optimization using the framework of velocity-constrained optimization. The experimental results show that our method can prune VGG19 and ResNet32 networks by more than 90% while preserving the high accuracy of the dense network.

Cite

Text

Oh et al. "Pruning Neural Networks with Velocity-Constrained Optimization." NeurIPS 2023 Workshops: OPT, 2023.

Markdown

[Oh et al. "Pruning Neural Networks with Velocity-Constrained Optimization." NeurIPS 2023 Workshops: OPT, 2023.](https://mlanthology.org/neuripsw/2023/oh2023neuripsw-pruning/)

BibTeX

@inproceedings{oh2023neuripsw-pruning,
  title     = {{Pruning Neural Networks with Velocity-Constrained Optimization}},
  author    = {Oh, Donghyun and Chung, Jinseok and Lee, Namhoon},
  booktitle = {NeurIPS 2023 Workshops: OPT},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/oh2023neuripsw-pruning/}
}