@article{nostalgicadamweightingmoreofthepast,
  title = {Nostalgic Adam: Weighting more of the past gradients when designing the adaptive learning rate},
  author = {Haiwen Huang and Chang Wang and Bin Dong},
  year = {2018},
  eprint = {1805.07557},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1805.07557v2},
}