Leave-One-Out Bounds for Kernel Methods
Author:
- 1 June 2003
- journal article
- Published by MIT Press in Neural Computation
- Vol. 15 (6) , 1397-1437
Abstract
In this article, we study leave-one-out style cross-validation bounds for kernel methods. The essential element in our analysis is a bound on the parameter estimation stability for regularized kernel formulations. Using this result, we derive bounds on expected leave-one-out cross-validation errors, which lead to expected generalization bounds for various kernel algorithms. In addition, we also obtain variance bounds for leave-oneout errors. We apply our analysis to some classification and regression problems and compare them with previous results.Keywords
This publication has 12 references indexed in Scilit:
- On the mathematical foundations of learningBulletin of the American Mathematical Society, 2001
- Regularization Networks and Support Vector MachinesAdvances in Computational Mathematics, 2000
- 10.1162/153244302760200704Applied Physics Letters, 2000
- Approximation properties of zonal function networks using scattered data on the sphereAdvances in Computational Mathematics, 1999
- Algorithmic Stability and Sanity-Check Bounds for Leave-One-Out Cross-ValidationNeural Computation, 1999
- Error Estimates for Interpolation by Compactly Supported Radial Basis Functions of Minimal DegreeJournal of Approximation Theory, 1998
- Stability results for scattered‐data interpolation on Euclidean spheresAdvances in Computational Mathematics, 1998
- Rates of convergence for minimum contrast estimatorsProbability Theory and Related Fields, 1993
- An Efron-Stein Inequality for Nonsymmetric StatisticsThe Annals of Statistics, 1986
- The Jackknife Estimate of VarianceThe Annals of Statistics, 1981