The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks

Itay M. Safran, Gilad Yehudai, Ohad Shamir. The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks. In Mikhail Belkin, Samory Kpotufe, editors, Conference on Learning Theory, COLT 2021, 15-19 August 2021, Boulder, Colorado, USA. Volume 134 of Proceedings of Machine Learning Research, pages 3889-3934, PMLR, 2021. [doi]

@inproceedings{SafranYS21,
  title = {The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks},
  author = {Itay M. Safran and Gilad Yehudai and Ohad Shamir},
  year = {2021},
  url = {http://proceedings.mlr.press/v134/safran21a.html},
  researchr = {https://researchr.org/publication/SafranYS21},
  cites = {0},
  citedby = {0},
  pages = {3889-3934},
  booktitle = {Conference on Learning Theory, COLT 2021, 15-19 August 2021, Boulder, Colorado, USA},
  editor = {Mikhail Belkin and Samory Kpotufe},
  volume = {134},
  series = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
}