Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?

Samet Oymak, Mahdi Soltanolkotabi. Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?. In Kamalika Chaudhuri, Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA. Volume 97 of Proceedings of Machine Learning Research, pages 4951-4960, PMLR, 2019. [doi]

@inproceedings{OymakS19,
  title = {Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?},
  author = {Samet Oymak and Mahdi Soltanolkotabi},
  year = {2019},
  url = {http://proceedings.mlr.press/v97/oymak19a.html},
  researchr = {https://researchr.org/publication/OymakS19},
  cites = {0},
  citedby = {0},
  pages = {4951-4960},
  booktitle = {Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA},
  editor = {Kamalika Chaudhuri and Ruslan Salakhutdinov},
  volume = {97},
  series = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
}