Landscape analysis for shallow neural networks: complete classification of critical points for affine target functions

19 March 2021

Papers citing "Landscape analysis for shallow neural networks: complete classification of critical points for affine target functions"

8 / 8 papers shown

Title
Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding Zhengqing Wu Berfin Simsek Francois Ged ODL 72 0 0 08 Feb 2024
Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation Arnulf Jentzen Adrian Riekert 45 23 0 09 Jul 2021
A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions Patrick Cheridito Arnulf Jentzen Adrian Riekert Florian Rossmannek 40 24 0 19 Feb 2021
On the Banach spaces associated with multi-layer ReLU networks: Function representation, approximation theory and gradient descent dynamics E. Weinan Stephan Wojtowytsch MLT 34 53 0 30 Jul 2020
Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss Lénaïc Chizat Francis R. Bach MLT 66 336 0 11 Feb 2020
Convergence rates for the stochastic gradient descent method for non-convex objective functions Benjamin J. Fehrman Benjamin Gess Arnulf Jentzen 56 101 0 02 Apr 2019
On the Power of Over-parametrization in Neural Networks with Quadratic Activation S. Du Jason D. Lee 105 271 0 03 Mar 2018
Theoretical insights into the optimization landscape of over-parameterized shallow neural networks Mahdi Soltanolkotabi Adel Javanmard Jason D. Lee 116 417 0 16 Jul 2017