The paper reports numerical evidence that the NTK equivalence theorem does not hold for finite-width neural networks trained with SGD, because trained networks and NTK kernel regressors behave differently when a layer is added.
The Database of AI Litigation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Issues with Neural Tangent Kernel Approach to Neural Networks
The paper reports numerical evidence that the NTK equivalence theorem does not hold for finite-width neural networks trained with SGD, because trained networks and NTK kernel regressors behave differently when a layer is added.