@article{onlargebatchtrainingfordeeplearning,
  title = {On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima},
  author = {Nitish Shirish Keskar and Dheevatsa Mudigere and Jorge Nocedal and Mikhail Smelyanskiy and Ping Tak Peter Tang},
  year = {2016},
  eprint = {1609.04836},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1609.04836v2},
}