Search Results for author:
Found 3 papers, 0 papers with code
The Optimality of Kernel Classifiers in Sobolev Space
Kernel methods are widely used in machine learning, especially for classification problems.
Generalization Ability of Wide Residual Networks
This uniform convergence further guarantees that the generalization error of the residual network converges to that of the kernel regression with respect to the RNTK.
Generalization Ability of Wide Neural Networks on $\mathbb{R}$
We perform a study on the generalization ability of the wide two-layer ReLU neural network on $\mathbb{R}$.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
