@article{dilocodistributedlowcommunicationtrainin,
  title = {DiLoCo: Distributed Low-Communication Training of Language Models},
  author = {Arthur Douillard and Qixuan Feng and Andrei A. Rusu and Rachita Chhaparia and Yani Donchev and Adhiguna Kuncoro and Marc'Aurelio Ranzato and Arthur Szlam and Jiajun Shen},
  year = {2023},
  eprint = {2311.08105},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.08105v3},
}