Description
We relate consistency or empirical risk minimization (ERM) with uniform convergence in probability over function classes. We prove generalization bounds for ERM in a bounded RKHS.Slides
Slides for this lecture: PS,PDFSuggested Reading
- V. N. Vapnik. The Nature of Statistical Learning Theory. Springer, 1995.
- Cucker and Smale. On the mathematical foundations of learning. Bulletin of the American Mathematical Society, 2002.
- Ding-Xuan Zhou. Capacity of Reproducing Kernel Spaces in Learning Theory. to appear in IEEE Trans. on Info. Theory, 2003.
- V. N. Vapnik and A. Ya. Chervonenkis. Necessary and Sufficient conditions for the uniform convergence of the means to their expectations. Probability Theory and Applications, 26, 532-553 1981.