Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth
and Initialization

v1v2 (latest)

Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization

1 February 2022

Mariia Seleznova

ArXiv (abs)PDF HTML

Papers citing "Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization"

5 / 5 papers shown

Title
Neural Tangent Kernel Analysis to Probe Convergence in Physics-informed Neural Solvers: PIKANs vs. PINNs Salah A Faroughi Farinaz Mostajeran 19 0 0 09 Jun 2025
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension Moritz Haas David Holzmüller U. V. Luxburg Ingo Steinwart MLT 121 14 0 23 May 2023
Approximation results for Gradient Descent trained Shallow Neural Networks in $1d$ R. Gentile G. Welper ODL 112 7 0 17 Sep 2022
Diverse Weight Averaging for Out-of-Distribution Generalization Alexandre Ramé Matthieu Kirchmeyer Thibaud Rahier A. Rakotomamonjy Patrick Gallinari Matthieu Cord OOD 266 138 0 19 May 2022
Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach Ryo Karakida S. Akaho S. Amari FedML 240 146 0 04 Jun 2018