Asymptotic Equivalence of Bayes Cross Validation and Widely Applicable Information Criterion in Singular Learning Theory
Sumio WatanabePublished in: CoRR (2010)
Keyphrases
- information criterion
- widely applicable
- learning theory
- marginal likelihood
- cross validation
- model selection
- hyperparameters
- variable selection
- support vector
- training set
- generalization error
- leave one out cross validation
- learning algorithm
- machine learning
- high dimensional
- reproducing kernel hilbert space
- feature selection