@article{distributedslideenablingtraininglarge,
  title = {Distributed SLIDE: Enabling Training Large Neural Networks on Low Bandwidth and Simple CPU-Clusters via Model Parallelism and Sparsity},
  author = {Minghao Yan and Nicholas Meisburger and Tharun Medini and Anshumali Shrivastava},
  year = {2022},
  eprint = {2201.12667},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2201.12667v1},
}