Model Selection Flashcards
1
Q
Occams razor
Training Error / Generalization Error
A
2
Q
Statistical Learning Theory
Learning Machines
A
3
Q
Statistical Learning Theory
MSE
A
4
Q
Bias Variance Tradeoff
A
- underfitting:
- high bias
- low variance
- overfitting:
- low bias
- high variance
5
Q
James Stein paradox
A
6
Q
No free lunch theorem
A
- Occams razor (simples model / most intuitive method is preferable):
- choice of model depends on scenario
- utilitaristic approach (lowest prediction error is preferable):
- without knowledge of the scenario, its impiossible to predict the prediction error
7
Q
Methods for model selection
A
8
Q
k-fold cross validation
A
- never use the test set!