Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, Tie-Yan Liu. On Layer Normalization in the Transformer Architecture. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event. Volume 119 of Proceedings of Machine Learning Research, pages 10524-10533, PMLR, 2020. [doi]
@inproceedings{XiongYHZZXZLWL20, title = {On Layer Normalization in the Transformer Architecture}, author = {Ruibin Xiong and Yunchang Yang and Di He and Kai Zheng and Shuxin Zheng and Chen Xing and Huishuai Zhang and Yanyan Lan and Liwei Wang and Tie-Yan Liu}, year = {2020}, url = {http://proceedings.mlr.press/v119/xiong20b.html}, researchr = {https://researchr.org/publication/XiongYHZZXZLWL20}, cites = {0}, citedby = {0}, pages = {10524-10533}, booktitle = {Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event}, volume = {119}, series = {Proceedings of Machine Learning Research}, publisher = {PMLR}, }