Lecture 15: Bayesian Interpretations of Regularization
We cover probabilistic interpretations of Tikhonov regularization -- specifically, regularized least squares. We show how ERM, linear RLS and kernel RLS can be derived in a Bayesian framework and discuss implications and possible limitations.
Slides for this lecture: PDF
- Vladimir I. Bogachev Gaussian Measures. Mathematical Surveys and Monographs, Volume 62, American Mathematical Society, 1998.