Optimizing Sparse Kernel Ridge Regression hyperparameters based on leave-one-out cross-validation.
Masayuki KarasuyamaRyohei NakanoPublished in: IJCNN (2008)
Keyphrases
- leave one out cross validation
- hyperparameters
- model selection
- cross validation
- gaussian process
- variable selection
- gaussian processes
- generalization error
- support vector
- bayesian inference
- regularization parameter
- sample size
- machine learning
- regression model
- random sampling
- kernel matrix
- feature selection
- em algorithm
- support vector machine
- bayesian framework
- closed form
- prior knowledge
- ls svm
- high dimensional
- training set