DPQ: Dynamic Pseudo-Mean Mixed-Precision Quantization for Pruned Neural Network

Pei et al. "DPQ: Dynamic Pseudo-Mean Mixed-Precision Quantization for Pruned Neural Network." Machine Learning, 2024. doi:10.1007/S10994-023-06453-3

[Pei et al. "DPQ: Dynamic Pseudo-Mean Mixed-Precision Quantization for Pruned Neural Network." Machine Learning, 2024.](https://mlanthology.org/mlj/2024/pei2024mlj-dpq/) doi:10.1007/S10994-023-06453-3

@article{pei2024mlj-dpq,
  title     = {{DPQ: Dynamic Pseudo-Mean Mixed-Precision Quantization for Pruned Neural Network}},
  author    = {Pei, Songwen and Wang, Jiyao and Zhang, Bingxue and Qin, Wei and Xue, Hai and Ye, Xiaochun and Chen, Mingsong},
  journal   = {Machine Learning},
  year      = {2024},
  pages     = {4099-4112},
  doi       = {10.1007/S10994-023-06453-3},
  volume    = {113},
  url       = {https://mlanthology.org/mlj/2024/pei2024mlj-dpq/}
}