Understanding Gradient Descent on the Edge of Stability in Deep Learning

@InProceedings{pmlr-v162-arora22a,
  title = 	 {Understanding Gradient Descent on the Edge of Stability in Deep Learning},
  author =       {Arora, Sanjeev and Li, Zhiyuan and Panigrahi, Abhishek},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {948--1024},
  year = 	 {2022},
  editor = 	 {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
  volume = 	 {162},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {17--23 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v162/arora22a/arora22a.pdf},
  url = 	 {https://proceedings.mlr.press/v162/arora22a.html},
  abstract = 	 {Deep learning experiments by \citet{cohen2021gradient} using deterministic Gradient Descent (GD) revealed an