An empirical comparison of V-fold penalisation and cross-validation for model selection in distribution-free regression.
Charanpal DhanjalNicolas BaskiotisStéphan ClémençonNicolas UsunierPublished in: Pattern Anal. Appl. (2016)
Keyphrases
- model selection
- cross validation
- distribution free
- regression model
- hyperparameters
- normal distribution
- generalization error
- sample size
- vc dimension
- variable selection
- parameter estimation
- sample complexity
- mixture model
- selection criterion
- gaussian process
- leave one out cross validation
- feature selection
- machine learning
- error estimation
- information criterion
- learning machines
- gaussian processes
- generalization bounds