How degenerate is the parametrization of neural networks with the ReLU activation function?

23 May 2019

Papers citing "How degenerate is the parametrization of neural networks with the ReLU activation function?"

10 / 10 papers shown

Title
Computability of Optimizers Yunseok Lee Holger Boche Gitta Kutyniok 29 16 0 15 Jan 2023
Local Identifiability of Deep ReLU Neural Networks: the Theory Joachim Bona-Pellissier Franccois Malgouyres F. Bachoc FAtt 67 6 0 15 Jun 2022
Learning ReLU networks to high uniform accuracy is intractable Julius Berner Philipp Grohs F. Voigtlaender 32 4 0 26 May 2022
Parameter identifiability of a deep feedforward ReLU neural network Joachim Bona-Pellissier François Bachoc François Malgouyres 41 14 0 24 Dec 2021
Non-convergence of stochastic gradient descent in the training of deep neural networks Patrick Cheridito Arnulf Jentzen Florian Rossmannek 14 37 0 12 Jun 2020
Universal Approximation with Deep Narrow Networks Patrick Kidger Terry Lyons 29 324 0 21 May 2019
Deep Neural Network Approximation Theory Dennis Elbrächter Dmytro Perekrestenko Philipp Grohs Helmut Bölcskei 14 207 0 08 Jan 2019
The Loss Surfaces of Multilayer Networks A. Choromańska Mikael Henaff Michaël Mathieu Gerard Ben Arous Yann LeCun ODL 179 1,185 0 30 Nov 2014
Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes Ohad Shamir Tong Zhang 101 570 0 08 Dec 2012
Improving neural networks by preventing co-adaptation of feature detectors Geoffrey E. Hinton Nitish Srivastava A. Krizhevsky Ilya Sutskever Ruslan Salakhutdinov VLM 266 7,634 0 03 Jul 2012