@article{stochasticgradientmethodswithlayerwise,
  title = {Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks},
  author = {Boris Ginsburg and Patrice Castonguay and Oleksii Hrinchuk and Oleksii Kuchaiev and Vitaly Lavrukhin and Ryan Leary and Jason Li and Huyen Nguyen and Yang Zhang and Jonathan M. Cohen},
  year = {2019},
  eprint = {1905.11286},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1905.11286v3},
}