Combined Pruning for Nested Cross-Validation to Accelerate Automated Hyperparameter Optimization for Embedded Feature Selection in High-Dimensional Data with Very Small Sample Sizes.
Sigrun MaySven HartmannFrank KlawonnPublished in: CoRR (2022)
Keyphrases
- model selection
- sample size
- cross validation
- high dimensional data
- small sample size
- feature selection
- small sample
- hyperparameters
- dimensionality reduction
- grid search
- high dimensionality
- regression problems
- variable selection
- high dimensional
- nearest neighbor
- parameter optimization
- low dimensional
- information criterion
- dimension reduction
- data sets
- data points
- selected features
- generalization error
- gaussian process
- regression model
- random sampling
- input space
- confidence intervals
- data analysis
- support vector
- linear discriminant analysis
- leave one out cross validation
- feature space
- input data
- feature extraction
- knn
- data mining
- optimality conditions
- text classification
- machine learning
- training set
- microarray data
- missing values