UAI 2021poster1 citations

Path-BN: Towards effective batch normalization in the Path Space for ReLU networks

Xufang Luo, Qi Meng, Wei Chen, Yunhong Wang, Tie-Yan Liu

Abstract

Neural networks with ReLU activation functions (abbrev. ReLU Networks), have demonstrated their success in many applications. Recently, researchers noticed that ReLU networks are positively scale-invariant (PSI) while the weights are not. This mismatch may lead to undesirable behaviors in the optimization process. Hence, some new algorithms that conduct optimization directly in the

BibTeX
@InProceedings{pmlr-v161-luo21b,
  title = 	 {Path-BN: Towards effective batch normalization in the Path Space for ReLU networks},
  author =       {Luo, Xufang and Meng, Qi and Chen, Wei and Wang, Yunhong and Liu, Tie-Yan},
  booktitle = 	 {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence},
  pages = 	 {834--843},
  year = 	 {2021},
  editor = 	 {de Campos, Cassio and Maathuis, Marloes H.},
  volume = 	 {161},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {27--30 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v161/luo21b/luo21b.pdf},
  url = 	 {https://proceedings.mlr.press/v161/luo21b.html},
  abstract = 	 {Neural networks with ReLU activation functions (abbrev. ReLU Networks), have demonstrated their success in many applications. Recently, researchers noticed that ReLU networks are positively scale-invariant (PSI) while the weights are not. This mismatch may lead to undesirable behaviors in the optimization process. Hence, some new algorithms that conduct optimization directly in the
Path-BN: Towards effective batch normalization in the Path Space for ReLU networks · UAI 2021