lecture07 - with beta=O(1/l and also to bound the loss...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
Lecture 07: Stability of Tikhonov Regularization Alex Rakhlin Description We briefly review the generalization bounds of last lecture before turning to our main goal -- using the stability approach to prove generalization bounds for Tikhonov regularization in RKHS. In order to apply the bounds, we need to prove that Tikhonov regularization is uniformly stable
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: with beta=O(1/l), and also to bound the loss function. In the process, we will gain additional insight into the mathematics of optimization and RKHS. Suggested Reading • O. Bousquet and A. Elisseeff. Stability and Generalization. Journal of Machine Learning Research, to appear, 2002....
View Full Document

{[ snackBarMessage ]}

Ask a homework question - tutors are online