@article{accumulateddecoupledlearningmitigating,
  title = {Accumulated Decoupled Learning: Mitigating Gradient Staleness in Inter-Layer Model Parallelization},
  author = {Huiping Zhuang and Zhiping Lin and Kar-Ann Toh},
  year = {2020},
  eprint = {2012.03747},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2012.03747v1},
}