How to allocate a restricted budget of leave-one-out assessments for effective model selection in machine learning: a comparison of state-of-the-art techniques.
Olivier CaelenGianluca BontempiPublished in: BNAIC (2005)
Keyphrases
- model selection
- cross validation
- machine learning
- hyperparameters
- parameter estimation
- statistical learning
- bayesian learning
- sample size
- meta learning
- feature selection
- model selection criteria
- error estimation
- selection criterion
- regression model
- variable selection
- motion segmentation
- unsupervised learning
- gaussian process
- generalization error
- covariate shift
- bayesian methods
- mixture model
- statistical inference
- generalization bounds
- support vector machine
- marginal likelihood
- automatic model selection
- support vector
- information criterion
- active learning
- machine learning methods
- machine learning algorithms