English

A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods

Machine Learning 2020-04-14 v1 Computer Vision and Pattern Recognition Neural and Evolutionary Computing

Abstract

To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and generally fall into two categories, i.e., static regularization-based pruning and dynamic regularization-based pruning. However, the former method currently suffers either complex workloads or accuracy degradation, while the latter one takes a long time to tune the parameters to achieve the desired pruning rate without accuracy loss. In this paper, we propose a unified DNN weight pruning framework with dynamically updated regularization terms bounded by the designated constraint, which can generate both non-structured sparsity and different kinds of structured sparsity. We also extend our method to an integrated framework for the combination of different DNN compression tasks.

Keywords

Cite

@article{arxiv.2004.05531,
  title  = {A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods},
  author = {Tianyun Zhang and Xiaolong Ma and Zheng Zhan and Shanglin Zhou and Minghai Qin and Fei Sun and Yen-Kuang Chen and Caiwen Ding and Makan Fardad and Yanzhi Wang},
  journal= {arXiv preprint arXiv:2004.05531},
  year   = {2020}
}
R2 v1 2026-06-23T14:48:19.754Z