Polylogarithmic Width Suffices for Gradient Descent to Achieve Arbitrarily Small Test Error with Shallow ReLU Networks

Ji and Telgarsky. "Polylogarithmic Width Suffices for Gradient Descent to Achieve Arbitrarily Small Test Error with Shallow ReLU Networks." International Conference on Learning Representations, 2020.

[Ji and Telgarsky. "Polylogarithmic Width Suffices for Gradient Descent to Achieve Arbitrarily Small Test Error with Shallow ReLU Networks." International Conference on Learning Representations, 2020.](https://mlanthology.org/iclr/2020/ji2020iclr-polylogarithmic/)

@inproceedings{ji2020iclr-polylogarithmic,
  title     = {{Polylogarithmic Width Suffices for Gradient Descent to Achieve Arbitrarily Small Test Error with Shallow ReLU Networks}},
  author    = {Ji, Ziwei and Telgarsky, Matus},
  booktitle = {International Conference on Learning Representations},
  year      = {2020},
  url       = {https://mlanthology.org/iclr/2020/ji2020iclr-polylogarithmic/}
}