EasyDeepLearn

What's the Bayesian interpretation of Ridge regression?

hard

Answer

  • Ridge regression is the maximum a posteriori (MAP) estimate under a Gaussian prior on the weights: w ~ N(0,  σ2/λ)N(0, \;\sigma^{2} / \lambda).
  • Equivalently, adding an L2 penalty on w is equivalent to assuming the coefficients are a priori small.
  • Lasso corresponds to a Laplace (double-exponential) prior on w, which has more probability mass at zero and heavier tails, explaining its sparsity behavior.
Check yourself — multiple choice
  • Ridge assumes a Laplace prior on the weights
  • Ridge is MAP under a Gaussian prior; Lasso is MAP under a Laplace prior
  • Ridge is Bayesian only if λ  =  0\lambda\; = \;0
  • Ridge does not have a Bayesian interpretation

L2 ≡ Gaussian prior (MAP); L1 ≡ Laplace prior — hence sparsity for Lasso.

#regularization#linear-models#theory

Practise Supervised Learning

215 interview questions in this topic.

Related questions