optimizer.bib

@inproceedings{Kingma_ICLR2015_Adam,
  author    = {Diederik P. Kingma and Jimmy Ba},
  booktitle = {International Conference on Learning Representations},
  title     = {Adam: {A} Method for Stochastic Optimization},
  url       = {http://arxiv.org/abs/1412.6980},
  year      = {2015}
}

@inproceedings{Loshchilov_ICLR2019_AdamW,
  author    = {Ilya Loshchilov and Frank Hutter},
  booktitle = {International Conference on Learning Representations},
  title     = {Decoupled Weight Decay Regularization},
  url       = {https://openreview.net/forum?id=Bkg6RiCqY7},
  year      = {2019}
}

@article{Tieleman_2012lecture_RMSprop,
  author  = {Tieleman, Tijmen and Hinton, Geoffrey},
  journal = {COURSERA: Neural networks for machine learning},
  number  = {2},
  pages   = {26--31},
  title   = {Lecture 6.5 -- rmsprop: Divide the gradient by a running average of its recent magnitude},
  url     = {https://www.youtube.com/watch?v=SJ48OZ_qlrc},
  volume  = {4},
  year    = {2012}
}