@inproceedings{parameternormgrowthduringtrainingof, title = {Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent}, author = {William Merrill and Vivek Ramanujan and Yoav Goldberg and Roy Schwartz and Noah Smith}, year = {2020}, booktitle = {EMNLP 2021 11}, eprint = {2010.09697}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2010.09697v5}, }