Efficient Model Selection for Large-Scale Nearest-Neighbor Data Mining.
Greg HamerlyGreg SpeeglePublished in: BNCOD (2010)
Keyphrases
- model selection
- nearest neighbor
- data mining
- cross validation
- meta learning
- machine learning
- parameter estimation
- hyperparameters
- model selection criteria
- regression model
- bayesian learning
- sample size
- statistical learning
- feature selection
- error estimation
- variable selection
- gaussian process
- motion segmentation
- real world
- selection criterion
- marginal likelihood
- mixture model
- generalization error
- knn
- bayesian methods
- automatic model selection
- statistical inference
- prior knowledge
- leave one out cross validation
- training data
- data sets