ResearchTrend.AI
On the Weight Dynamics of Deep Normalized Networks
v1v2v3 (latest)

On the Weight Dynamics of Deep Normalized Networks

International Conference on Machine Learning (ICML), 2023
Christian H. X. Ali Mehmeti-Göpel
Michael Wand
ArXiv (abs)PDFHTML

Papers citing "On the Weight Dynamics of Deep Normalized Networks"

3 / 3 papers shown
Title
Can Training Dynamics of Scale-Invariant Neural Networks Be Explained by the Thermodynamics of an Ideal Gas?
Can Training Dynamics of Scale-Invariant Neural Networks Be Explained by the Thermodynamics of an Ideal Gas?
Ildus Sadrtdinov
E. Lobacheva
Ivan Klimov
Mikhail I. Katsnelson
Dmitry Vetrov
AI4CE
72
0
0
10 Nov 2025
Weight Decay may matter more than muP for Learning Rate Transfer in Practice
Weight Decay may matter more than muP for Learning Rate Transfer in Practice
Atli Kosson
Jeremy Welborn
Yang Liu
Martin Jaggi
Xi Chen
40
1
0
21 Oct 2025
ResNets Are Deeper Than You Think
ResNets Are Deeper Than You Think
Christian H.X. Ali Mehmeti-Göpel
Michael Wand
108
0
0
17 Jun 2025