Leave-One-Out Bounds for Kernel Methods

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.

Cite

Text

Zhang. "Leave-One-Out Bounds for Kernel Methods." Neural Computation, 2003. doi:10.1162/089976603321780326

Markdown

[Zhang. "Leave-One-Out Bounds for Kernel Methods." Neural Computation, 2003.](https://mlanthology.org/neco/2003/zhang2003neco-leaveoneout/) doi:10.1162/089976603321780326

BibTeX

@article{zhang2003neco-leaveoneout,
  title     = {{Leave-One-Out Bounds for Kernel Methods}},
  author    = {Zhang, Tong},
  journal   = {Neural Computation},
  year      = {2003},
  pages     = {1397-1437},
  doi       = {10.1162/089976603321780326},
  volume    = {15},
  url       = {https://mlanthology.org/neco/2003/zhang2003neco-leaveoneout/}
}