@article{dataparalleldistributedtrainingofvery,
  title = {Data-parallel distributed training of very large models beyond GPU capacity},
  author = {Samuel Matzek and Max Grossman and Minsik Cho and Anar Yusifov and Bryant Nelson and Amit Juneja},
  year = {2018},
  eprint = {1811.12174},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1811.12174v1},
}