Gradient Descent Optimizes Over-Parameterized Deep ReLU Networks

Zou et al. "Gradient Descent Optimizes Over-Parameterized Deep ReLU Networks." Machine Learning, 2020. doi:10.1007/S10994-019-05839-6

[Zou et al. "Gradient Descent Optimizes Over-Parameterized Deep ReLU Networks." Machine Learning, 2020.](https://mlanthology.org/mlj/2020/zou2020mlj-gradient/) doi:10.1007/S10994-019-05839-6

@article{zou2020mlj-gradient,
  title     = {{Gradient Descent Optimizes Over-Parameterized Deep ReLU Networks}},
  author    = {Zou, Difan and Cao, Yuan and Zhou, Dongruo and Gu, Quanquan},
  journal   = {Machine Learning},
  year      = {2020},
  pages     = {467-492},
  doi       = {10.1007/S10994-019-05839-6},
  volume    = {109},
  url       = {https://mlanthology.org/mlj/2020/zou2020mlj-gradient/}
}