A cross-validation approach to bandwidth selection for a kernel-based estimate of the density of a conditional expectation.

Athanassios N. Avramidis

Published in: WSC (2011)

Keyphrases

cross validation
conditional expectation
generalization error
support vector
model selection
weighted least squares
error estimates
hyperparameters
unseen data
training set
ls svm
kernel methods
information criterion
estimation error
data mining
neural network
parameter estimation
learning process
decision trees