@inproceedings{dataparallelismintrainingsparseneural,
  title = {Understanding the Effects of Data Parallelism and Sparsity on Neural Network Training},
  author = {Namhoon Lee and Thalaiyasingam Ajanthan and Philip H. S. Torr and Martin Jaggi},
  year = {2020},
  booktitle = {ICLR 2021 1},
  eprint = {2003.11316},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2003.11316v3},
}