@article{adistributeddataparallelpytorch,
  title = {A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale},
  author = {Hao-Jun Michael Shi and Tsung-Hsien Lee and Shintaro Iwasaki and Jose Gallego-Posada and Zhijing Li and Kaushik Rangadurai and Dheevatsa Mudigere and Michael Rabbat},
  year = {2023},
  eprint = {2309.06497},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2309.06497v1},
}