EasyDeepLearn

When would you use robust regression (Huber, RANSAC) instead of OLS?

medium

Answer

  • Use robust regression when the data contains outliers that shouldn't dominate the fit.
  • OLS minimizes squared error, so a single large-residual point can pull the line dramatically.
  • Huber loss is quadratic near zero and linear in the tails, giving less weight to outliers.
  • RANSAC fits on random subsets and picks the fit with the most inliers — great when up to ~50% of points are contaminated.
  • Quantile regression is another robust option that models a specific quantile.
Check yourself — multiple choice
  • Robust regression is faster than OLS
  • It downweights or excludes outliers so they don't dominate the fit
  • It requires normally distributed features
  • It only works for classification

Robust methods (Huber, RANSAC) limit outlier influence — OLS is very sensitive to them.

#linear-regression#outliers

Practise Supervised Learning

215 interview questions in this topic.

Related questions