@article{dl-01-1,
  title = {{Stochastic Gradient Descent as Approximate Bayesian Inference}},
  author = {Mandt, Stephan and Hoffman, Matthew D. and Blei, David M.},
  journal = {Journal of Machine Learning Research 18(134)},
  year = {2017},
  url = {https://jmlr.org/papers/v18/17-214.html}
}

@misc{dl-01-2,
  title = {{A Bayesian Perspective on Generalization and Stochastic Gradient Descent}},
  author = {Smith, Samuel L. and Le, Quoc V.},
  howpublished = {arXiv:1710.06451},
  year = {2017},
  doi = {10.48550/arXiv.1710.06451},
  url = {https://arxiv.org/abs/1710.06451}
}

@misc{dl-01-3,
  title = {{An Empirical Model of Large-Batch Training}},
  author = {McCandlish, Sam and Kaplan, Jared and Amodei, Dario and {OpenAI Dota Team}},
  howpublished = {arXiv:1812.06162},
  year = {2018},
  doi = {10.48550/arXiv.1812.06162},
  url = {https://arxiv.org/abs/1812.06162}
}