NIPS Proceedingsβ

Jeffrey Pennington

5 Papers

  • Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent (2019)
  • The Spectrum of the Fisher Information Matrix of a Single-Hidden-Layer Neural Network (2018)
  • Nonlinear random matrix theory for deep learning (2017)
  • Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice (2017)
  • Spherical Random Features for Polynomial Kernels (2015)