Building diverse and optimized ensembles of gradient boosted trees for high-dimensional data.
Tarek AbdunabiOtman A. BasirPublished in: CCIS (2014)
Keyphrases
- high dimensional data
- decision trees
- low dimensional
- dimensionality reduction
- nearest neighbor
- random forests
- data sets
- high dimensional
- subspace clustering
- high dimensions
- data analysis
- data points
- high dimensionality
- dimension reduction
- manifold learning
- clustering high dimensional data
- similarity search
- original data
- input space
- sparse representation
- data distribution
- high dimensional data sets
- small sample size
- high dimensional datasets
- dimensional data
- variable weighting
- text data
- ensemble methods
- regression problems
- variable selection
- linear discriminant analysis
- nonlinear dimensionality reduction
- tree structure
- decision stumps
- subspace learning
- high dimensional spaces
- training data
- image processing
- real world