Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape

31 May 2023

Papers citing "Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape"

6 / 6 papers shown

Title
Derivation of effective gradient flow equations and dynamical truncation of training data in Deep Learning Thomas Chen 34 0 0 13 Jan 2025
Gradient flow in parameter space is equivalent to linear interpolation in output space Thomas Chen Patrícia Muñoz Ewald 25 1 0 02 Aug 2024
Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension Kedar Karhadkar Michael Murray Guido Montúfar 32 2 0 23 May 2024
Continual Learning with Weight Interpolation Jkedrzej Kozal Jan Wasilewski Bartosz Krawczyk Michal Wo'zniak CLL MoMe 34 6 0 05 Apr 2024
The Real Tropical Geometry of Neural Networks Marie-Charlotte Brandenburg Georg Loho Guido Montúfar 54 7 0 18 Mar 2024
Functional dimension of feedforward ReLU neural networks J. E. Grigsby Kathryn A. Lindsey R. Meyerhoff Chen-Chun Wu 27 11 0 08 Sep 2022