Lecture 17: Rademacher Averages and Symmetrization
Alex Rakhlin


Description

We introduce the idea of symmetrization and relate the supremum of an empirical process to the supremum of a Rademacher process. Properties of Rademacher Averages are discussed.

Slides

Slides for this lecture: PS,PDF.

Suggested Reading

S. Mendelson, A few notes on Statistical Learning Theory, In Advanced Lectures in Machine Learning, (S. Mendelson, A.J. Smola Eds), LNCS 2600, 1-40, Springer 2003.