Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs

Alon Brutzkus, Amir Globerson. Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs. In Doina Precup, Yee Whye Teh, editors, Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017. Volume 70 of JMLR Workshop and Conference Proceedings, pages 605-614, JMLR.org, 2017. [doi]

@inproceedings{BrutzkusG17,
  title = {Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs},
  author = {Alon Brutzkus and Amir Globerson},
  year = {2017},
  url = {http://proceedings.mlr.press/v70/brutzkus17a.html},
  researchr = {https://researchr.org/publication/BrutzkusG17},
  cites = {0},
  citedby = {0},
  pages = {605-614},
  booktitle = {Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017},
  editor = {Doina Precup and Yee Whye Teh},
  volume = {70},
  series = {JMLR Workshop and Conference Proceedings},
  publisher = {JMLR.org},
}