Trading Variance Reduction with Unbiasedness: The Regularized Subspace Information Criterion for Robust Model Selection in Kernel Regression.
Masashi SugiyamaMotoaki KawanabeKlaus-Robert MüllerPublished in: Neural Comput. (2004)
Keyphrases
- model selection
- subspace information criterion
- kernel regression
- regression model
- variance reduction
- sample size
- generalization error
- cross validation
- parameter estimation
- hyperparameters
- machine learning
- variable selection
- feature selection
- least squares
- regression methods
- random sampling
- image sequences
- training data
- monte carlo
- data sets
- confidence intervals
- training set
- data mining