%0 Conference Paper %1 conf/icml/ZhaiLLBR0GS23 %A Zhai, Shuangfei %A Likhomanenko, Tatiana %A Littwin, Etai %A Busbridge, Dan %A Ramapuram, Jason %A Zhang, Yizhe %A Gu, Jiatao %A Susskind, Joshua M. %B ICML %D 2023 %E Krause, Andreas %E Brunskill, Emma %E Cho, Kyunghyun %E Engelhardt, Barbara %E Sabato, Sivan %E Scarlett, Jonathan %I PMLR %K dblp %P 40770-40803 %T Stabilizing Transformer Training by Preventing Attention Entropy Collapse. %U http://dblp.uni-trier.de/db/conf/icml/icml2023.html#ZhaiLLBR0GS23 %V 202

@inproceedings{conf/icml/ZhaiLLBR0GS23, added-at = {2023-08-28T00:00:00.000+0200}, author = {Zhai, Shuangfei and Likhomanenko, Tatiana and Littwin, Etai and Busbridge, Dan and Ramapuram, Jason and Zhang, Yizhe and Gu, Jiatao and Susskind, Joshua M.}, biburl = {https://www.bibsonomy.org/bibtex/2f6f538634f9a5e1a126ec3c21e167bf8/dblp}, booktitle = {ICML}, crossref = {conf/icml/2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, ee = {https://proceedings.mlr.press/v202/zhai23a.html}, interhash = {b9a9081ce99f0816a42fe0d7dde275bf}, intrahash = {f6f538634f9a5e1a126ec3c21e167bf8}, keywords = {dblp}, pages = {40770-40803}, publisher = {PMLR}, series = {Proceedings of Machine Learning Research}, timestamp = {2024-04-10T01:43:32.000+0200}, title = {Stabilizing Transformer Training by Preventing Attention Entropy Collapse.}, url = {http://dblp.uni-trier.de/db/conf/icml/icml2023.html#ZhaiLLBR0GS23}, volume = 202, year = 2023 }