Model Selection by Bootstrap Penalization for Classification.
Magalie FromontPublished in: COLT (2004)
Keyphrases
- model selection
- cross validation
- generalization error
- hyperparameters
- variable selection
- sample size
- statistical learning
- bayesian learning
- machine learning
- leave one out cross validation
- regression model
- selection criterion
- parameter estimation
- hypothesis tests
- model selection criteria
- meta learning
- information criterion
- mixture model
- error estimation
- statistical inference
- support vector
- feature selection
- unsupervised learning
- training set
- generalization bounds
- classification accuracy
- marginal likelihood
- closed form
- bayesian information criterion
- knn
- active learning
- feature space
- learning algorithm