EasyDeepLearn

MSE vs MAE for regression — when is each preferred?

easy

Answer

  • MSE (L2): differentiable everywhere, penalizes large errors quadratically → sensitive to outliers, gradients are proportional to error size.
  • MAE (L1): penalizes linearly → robust to outliers but not differentiable at 0.
  • Choose MSE when errors are Gaussian-ish and outliers are rare; choose MAE when the target has heavy tails or you want the median rather than the mean.
  • Huber loss is the practical compromise.
Check yourself — multiple choice
  • MSE is robust to outliers
  • MSE penalizes large errors more (Gaussian-friendly, outlier-sensitive); MAE is robust but non-smooth at 0
  • MSE and MAE are identical
  • MAE has no gradient anywhere

MSE ↔ Gaussian noise / mean; MAE ↔ Laplace noise / median; Huber compromises.

#losses#fundamentals

Practise Deep Learning

214 interview questions in this topic.

Related questions