In the bias-variance tradeoff, what usually happens to the variance as the model complexity (degrees of freedom) increases?
Show answer
It increases
High-complexity models tend to be more sensitive to the specific noise in the training set (high variance), whereas low-complexity models may fail to capture the underlying patterns (high bias).
Also asked as:
- In the bias-variance tradeoff, how does increasing a model's degrees of freedom typically affect its variance?