A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel.
Mohamad Amin MohamadiWonho BaeDanica J. SutherlandPublished in: ICML (2023)
Keyphrases
- network architecture
- kernel methods
- neural network
- kernel regression
- approximation algorithms
- theoretical analysis
- kernel function
- closed form
- error bounds
- input space
- convolution kernel
- series expansion
- approximation error
- empirical data
- relative error
- artificial neural networks
- approximation methods
- feature space
- polynomial kernels
- support vector
- machine learning