@misc{chen2022towards,
  title={Towards Understanding Mixture of Experts in Deep Learning},
  author={Zixiang Chen and Yihe Deng and Yue Wu and Quanquan Gu and Yuanzhi Li},
  year={2022},
  eprint={2208.02813},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2208.02813}
}