@misc{dl-15-1,
  title = {{Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer}},
  author = {Shazeer, Noam and Mirhoseini, Azalia and Maziarz, Krzysztof and Davis, Andy and Le, Quoc and Hinton, Geoffrey and Dean, Jeff},
  howpublished = {arXiv preprint},
  year = {2017},
  doi = {10.48550/arXiv.1701.06538},
  url = {https://arxiv.org/abs/1701.06538}
}

@article{dl-15-2,
  title = {{Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity}},
  author = {Fedus, William and Zoph, Barret and Shazeer, Noam},
  journal = {Journal of Machine Learning Research, 23(120):1-39},
  year = {2022},
  url = {https://jmlr.org/papers/v23/21-0998.html}
}

@misc{dl-15-3,
  title = {{GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding}},
  author = {Lepikhin, Dmitry and Lee, HyoukJoong and Xu, Yuanzhong and Chen, Dehao and Firat, Orhan and Huang, Yanping and Krikun, Maxim and Shazeer, Noam and Chen, Zhifeng},
  howpublished = {arXiv preprint},
  year = {2020},
  doi = {10.48550/arXiv.2006.16668},
  url = {https://arxiv.org/abs/2006.16668}
}