%0 Conference Paper %1 conf/emnlp/MerrillRG0S21 %A Merrill, William %A Ramanujan, Vivek %A Goldberg, Yoav %A Schwartz, Roy %A Smith, Noah A. %B EMNLP (1) %D 2021 %E Moens, Marie-Francine %E Huang, Xuanjing %E Specia, Lucia %E tau Yih, Scott Wen %I Association for Computational Linguistics %K dblp %P 1766-1781 %T Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent. %U http://dblp.uni-trier.de/db/conf/emnlp/emnlp2021-1.html#MerrillRG0S21

@inproceedings{conf/emnlp/MerrillRG0S21, added-at = {2022-01-20T00:00:00.000+0100}, author = {Merrill, William and Ramanujan, Vivek and Goldberg, Yoav and Schwartz, Roy and Smith, Noah A.}, biburl = {https://www.bibsonomy.org/bibtex/2c7d70e9e1a22baee8376165053d995d0/dblp}, booktitle = {EMNLP (1)}, crossref = {conf/emnlp/2021-1}, editor = {Moens, Marie-Francine and Huang, Xuanjing and Specia, Lucia and tau Yih, Scott Wen}, ee = {https://aclanthology.org/2021.emnlp-main.133}, interhash = {d6a369d4b31d1b8d49895c0580343bb6}, intrahash = {c7d70e9e1a22baee8376165053d995d0}, keywords = {dblp}, pages = {1766-1781}, publisher = {Association for Computational Linguistics}, timestamp = {2024-04-09T22:57:48.000+0200}, title = {Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent.}, url = {http://dblp.uni-trier.de/db/conf/emnlp/emnlp2021-1.html#MerrillRG0S21}, year = 2021 }