Tight conditions for when the NTK approximation is valid

Enric Boix-Adserà, Etai Littwin

Abstract: We study when the neural tangent kernel (NTK) approximation is valid for training a model with the square loss. In the lazy training setting of Chizat et al. 2019, we show that rescaling the model by a factor of $\alpha = O(T)$ suffices for the NTK approximation to be valid until training time $T$. Our bound is tight and improves on the previous bound of Chizat et al. 2019, which required a larger rescaling factor of $\alpha = O(T^2)$.

Submission Length: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Murat_A_Erdogdu1

License: Creative Commons Attribution 4.0 International (CC BY 4.0)

Submission Number: 1179