The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization.
Ben AdlamJeffrey PenningtonPublished in: CoRR (2020)
Keyphrases
- high dimensions
- multiscale
- high dimensional
- high dimensional data
- high dimensional spaces
- network architecture
- kernel methods
- kernel function
- indexing schemes
- neural network
- poor quality
- image representation
- scale space
- feature space
- pattern recognition
- high quality
- region of interest
- coarse to fine
- motion estimation
- data analysis