Relating Regularization and Generalization through the Intrinsic Dimension of Activations

23 November 2022

Papers citing "Relating Regularization and Generalization through the Intrinsic Dimension of Activations"

4 / 4 papers shown

Title
Why neural networks find simple solutions: the many regularizers of geometric complexity Benoit Dherin Michael Munn M. Rosca David Barrett 53 30 0 27 Sep 2022
Tangent Space and Dimension Estimation with the Wasserstein Distance Uzu Lim Harald Oberhauser Vidit Nanda 37 8 0 12 Oct 2021
The Foes of Neural Network's Data Efficiency Among Unnecessary Input Dimensions Vanessa D’Amario S. Srivastava Tomotake Sasaki Xavier Boix AAML 14 2 0 13 Jul 2021
The Intrinsic Dimension of Images and Its Impact on Learning Phillip E. Pope Chen Zhu Ahmed Abdelkader Micah Goldblum Tom Goldstein 189 259 0 18 Apr 2021