BibTeX record conf/icml/ZhaiLLBR0GS23

• > Home > conf/icml/ZhaiLLBR0GS23

@inproceedings{DBLP:conf/icml/ZhaiLLBR0GS23,
  author       = {Shuangfei Zhai and
                  Tatiana Likhomanenko and
                  Etai Littwin and
                  Dan Busbridge and
                  Jason Ramapuram and
                  Yizhe Zhang and
                  Jiatao Gu and
                  Joshua M. Susskind},
  editor       = {Andreas Krause and
                  Emma Brunskill and
                  Kyunghyun Cho and
                  Barbara Engelhardt and
                  Sivan Sabato and
                  Jonathan Scarlett},
  title        = {Stabilizing Transformer Training by Preventing Attention Entropy Collapse},
  booktitle    = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
                  2023, Honolulu, Hawaii, {USA}},
  series       = {Proceedings of Machine Learning Research},
  volume       = {202},
  pages        = {40770--40803},
  publisher    = {{PMLR}},
  year         = {2023},
  url          = {https://proceedings.mlr.press/v202/zhai23a.html},
  timestamp    = {Mon, 28 Aug 2023 17:23:09 +0200},
  biburl       = {https://dblp.org/rec/conf/icml/ZhaiLLBR0GS23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}