Deep networks are reproducing kernel chains
From MaRDI portal
Cites work
- Banach space representer theorems for neural networks and ridge splines
- Breaking the curse of dimensionality with convex neural networks
- Embeddings between Barron spaces with higher-order activation functions
- Explicit representations for Banach subspaces of Lizorkin distributions
- Generalization properties of hyper-RKHS and its applications
- Learning a sparse representation of Barron functions with the inverse scale space flow
- On reproducing kernel Banach spaces: generic definitions and unified framework of constructions
- Random neural networks in the infinite width limit as Gaussian processes
- Representation formulas and pointwise properties for Barron functions
- Sparsifying dimensionality reduction of PDE solution data with Bregman learning
- The Barron space and the flow-induced function spaces for neural network models
- Theory of Reproducing Kernels
- Understanding neural networks with reproducing kernel Banach spaces
- What Kinds of Functions Do Deep Neural Networks Learn? Insights from Variational Spline Theory
This page was built for publication: Deep networks are reproducing kernel chains
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7446980)