Quasi Black Hole Effect of Gradient Descent in Large Dimension: Consequence on Neural Network Learning

Anne Bouillard, Philippe Jacquet. Quasi Black Hole Effect of Gradient Descent in Large Dimension: Consequence on Neural Network Learning. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2019, Brighton, United Kingdom, May 12-17, 2019. pages 8365-8369, IEEE, 2019. [doi]

@inproceedings{BouillardJ19,
  title = {Quasi Black Hole Effect of Gradient Descent in Large Dimension: Consequence on Neural Network Learning},
  author = {Anne Bouillard and Philippe Jacquet},
  year = {2019},
  doi = {10.1109/ICASSP.2019.8683250},
  url = {https://doi.org/10.1109/ICASSP.2019.8683250},
  researchr = {https://researchr.org/publication/BouillardJ19},
  cites = {0},
  citedby = {0},
  pages = {8365-8369},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2019, Brighton, United Kingdom, May 12-17, 2019},
  publisher = {IEEE},
  isbn = {978-1-4799-8131-1},
}