Publications of Torsten Hoefler

Yunqiang Li, Jan C van Gemert, Torsten Hoefler, Bert Moons, Evangelos Eleftheriou, Bram-Ernst Verhoef:

Differentiable Transportation Pruning

(2023 IEEE/CVF International Conference on Computer Vision (ICCV). Oct. 2023)

Publisher Reference

Abstract

Deep learning algorithms are increasingly employed at the edge. However, edge devices are resource constrained and thus require efficient deployment of deep neural networks. Pruning methods are a key tool for edge deployment as they can improve storage, compute, memory bandwidth, and energy usage. In this paper we propose a novel accurate pruning technique that allows precise control over the output network size. Our method uses an efficient optimal transportation scheme which we make end-to-end differentiable and which automatically tunes the exploration-exploitation behavior of the algorithm to find accurate sparse sub-networks. We show that our method achieves state-of-the-art performance compared to previous pruning methods on 3 different datasets, using 5 different models, across a wide range of pruning ratios, and with two types of sparsity budgets and pruning granularities.

Documents

Publisher URL: https://doi.ieeecomputersociety.org/10.1109/ICCV51070.2023.01555download article:

BibTeX

@article{yunquiang-trans_pruning,
  author={Yunqiang Li and Jan C van Gemert and Torsten Hoefler and Bert Moons and Evangelos Eleftheriou and Bram-Ernst Verhoef},
  title={{Differentiable Transportation Pruning}},
  journal={2023 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2023},
  month={Oct.},
  source={http://www.unixer.de/~htor/publications/},
}


serving: 18.190.176.176:32323	© Torsten Hoefler