When Do Neural Networks Outperform Kernel Methods?

Behrooz Ghorbani Song Mei Theodor Misiakiewicz Andrea Montanari

Published in: CoRR (2020)

Keyphrases

kernel methods
neural network
kernel function
learning problems
feature space
kernel matrix
support vector
support vector machine

reproducing kernel hilbert space
machine learning
similarity function
kernel pca
back propagation
learning tasks
multiple kernel learning

artificial neural networks
kernel trick
kernel matrices
high dimensional feature space
neural network model
learning frameworks
kernel ridge regression

kernel based clustering
positive semidefinite
multiple kernel
kernel principal component analysis
kernel learning
support vector regression
learning algorithm