What's the main risk of polynomial regression?
easyAnswer
- High-degree polynomial features overfit dramatically: they can hit training points exactly while oscillating wildly between them (Runge's phenomenon).
- Predictions extrapolate very poorly outside the training range.
- Alternatives: use splines (piecewise low-degree polynomials with continuity), local polynomials (LOESS), regularized polynomials, or non-parametric models like trees.
- If you must use polynomials, standardize inputs and combine with L2 regularization.
Check yourself — multiple choice
- It's always worse than linear regression
- High-degree polynomials overfit and extrapolate badly (Runge's phenomenon)
- Polynomials can't be regularized
- It works only for one feature
High-degree polynomials overfit and oscillate; splines or regularized fits are usually safer.
#linear-regression#features#regularization
Practise Supervised Learning
215 interview questions in this topic.
Related questions
- How do you handle strong multicollinearity in a linear model?
- What is VIF and when do you worry about multicollinearity?
- When should you add interaction features to a linear model?
- When would you use Group Lasso instead of standard Lasso?
- How do you detect and fix overfitting?
- L1 vs L2 regularization — what's the difference?