ReLU soothes the NTK condition number and accelerates optimization for wide neural networks

15 May 2023

Papers citing "ReLU soothes the NTK condition number and accelerates optimization for wide neural networks"

2 / 2 papers shown

Title
Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks Jim Zhao Sidak Pal Singh Aurelien Lucchi AI4CE 45 0 0 04 Nov 2024
Fast Training of Sinusoidal Neural Fields via Scaling Initialization Taesun Yeom Sangyoon Lee Jaeho Lee 55 2 0 07 Oct 2024