@inproceedings{merrill-etal-2021-effects,
    title = "Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent",
    author = "Merrill, William  and
      Ramanujan, Vivek  and
      Goldberg, Yoav  and
      Schwartz, Roy  and
      Smith, Noah A.",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.emnlp-main.133/",
    doi = "10.18653/v1/2021.emnlp-main.133",
    pages = "1766--1781"
}