Effect of mixing probabilities on the bias of cross-validation under separate sampling.
Amin ZollanvariUlisses M. Braga-NetoEdward R. DoughertyPublished in: GENSiPS (2013)
Keyphrases
- cross validation
- model selection
- variable selection
- hyperparameters
- support vector
- regression problems
- regularization parameter
- cross validated
- generalization error
- training set
- probability distribution
- error estimates
- unseen data
- sample size
- information criterion
- parameter space
- meta learning
- feature extraction
- face recognition
- feature selection
- nearest neighbor classifiers
- grid search
- neural network