@misc{dl3-a01-1,
  title = {Attention Is All You Need},
  author = {Ashish Vaswani and Noam Shazeer and Niki Parmar and Jakob Uszkoreit and Llion Jones and Aidan N. Gomez and Lukasz Kaiser and Illia Polosukhin},
  year = {2017},
  url = {https://arxiv.org/abs/1706.03762},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {1706.03762},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a01-2,
  title = {Low-Rank Bottleneck in Multi-head Attention Models},
  author = {Srinadh Bhojanapalli and Chulhee Yun and Ankit Singh Rawat and Sashank J. Reddi and Sanjiv Kumar},
  year = {2020},
  url = {https://arxiv.org/abs/2002.07028},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2002.07028},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a01-3,
  title = {Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth},
  author = {Yihe Dong and Jean-Baptiste Cordonnier and Andreas Loukas},
  year = {2021},
  url = {https://arxiv.org/abs/2103.03404},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2103.03404},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a01-4,
  title = {Are Transformers universal approximators of sequence-to-sequence functions?},
  author = {Chulhee Yun and Srinadh Bhojanapalli and Ankit Singh Rawat and Sashank J. Reddi and Sanjiv Kumar},
  year = {2019},
  url = {https://arxiv.org/abs/1912.10077},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {1912.10077},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a01-5,
  title = {Rethinking Attention with Performers},
  author = {Krzysztof Choromanski and Valerii Likhosherstov and David Dohan and Xingyou Song and Andreea Gane and Tamas Sarlos and Peter Hawkins and Jared Davis and Afroz Mohiuddin and Lukasz Kaiser and David Belanger and Lucy Colwell and Adrian Weller},
  year = {2020},
  url = {https://arxiv.org/abs/2009.14794},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2009.14794},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-a01-6,
  title = {Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention},
  author = {Angelos Katharopoulos and Apoorv Vyas and Nikolaos Pappas and François Fleuret},
  year = {2020},
  url = {https://arxiv.org/abs/2006.16236},
  howpublished = {arXiv primary author manuscript},
  archivePrefix = {arXiv},
  eprint = {2006.16236},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}