@inproceedings{towardstheoreticallyunderstandingwhysgd,
  title = {Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning},
  author = {Pan Zhou and Jiashi Feng and Chao Ma and Caiming Xiong and Steven Hoi and Weinan E},
  year = {2020},
  booktitle = {NeurIPS 2020 12},
  eprint = {2010.05627},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2010.05627v2},
}