AI engineering glossary · ML fundamentals
What is model variance?
Model variance (also called Variance error): The part of prediction error that comes from a model being too sensitive to the particular training sample. Retrain a high-variance model on a slightly different sample and its predictions change a lot. Flexible models with little data suffer most, and averaging or regularisation reduces it.
Model variance: an example
Two deep trees trained on different random halves of the same customer data give quite different predictions for the same new customer.
Related terms
More ML fundamentals terms
- Nested cross-validation
- No free lunch theorem
- Noise
- Non-parametric model
- Occam's razor
- Online learning
- Out-of-distribution
- Outlier
Where you learn it
Model variance is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.