@inproceedings{rethinkingbatchnormalizationin, title = {PowerNorm: Rethinking Batch Normalization in Transformers}, author = {Sheng Shen and Zhewei Yao and Amir Gholami and Michael W. Mahoney and Kurt Keutzer}, year = {2020}, booktitle = {ICML 2020 1}, eprint = {2003.07845}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2003.07845v2}, }