Spectral Regularization
Lorenzo Rosasco
Description
In this class we show how a large class of techniques for finding stable solutions to
matrix inversion problems give rise to consistent kernel methods. Regularized least-squares
can be shown to be an instance from this general class of techniques.
Slides
Slides for this lecture: PDF
Suggested Reading
-
Mosci, S., Rosasco, L. and Verri A.
" Dimensionality reduction and generalization ",
ACM International Conference Proceeding Series; Vol. 227 archive Proceedings of
the 24th International Conference on Machine Learning
-
Yao Y., Rosasco L. and Caponnetto, A.
"On Early Stopping in Gradient Descent Learning",
to be published in Constructive Approximation.
-
Lo Gerfo L., Rosasco L., Odone F., De Vito E. and Verri, A.
Spectral Algorithms for Supervised Learning,
to appear in Neural Computation.
- Bauer F., Pereverzev S. and Rosasco L.
"On Regularization Algorithms in Learning Theory",
J. Complexity 23(1): 52-72 (2007) (Technical Report DISI-TR-05-19).