ML Anthology

An Identity for Kernel Ridge Regression

Fedor Zhdanov, Yuri Kalnishkan
ALT 2010 pp. 405-419
doi:10.1007/978-3-642-16108-7_32 /alt/2010/zhdanov2010alt-identity/

Abstract

This paper provides a probabilistic derivation of an identity connecting the square loss of ridge regression in on-line mode with the loss of a retrospectively best regressor. Some corollaries of the identity providing upper bounds for the cumulative loss of on-line ridge regression are also discussed.

PDF ALT Semantic Scholar

Cite

Text

Zhdanov and Kalnishkan. "An Identity for Kernel Ridge Regression." International Conference on Algorithmic Learning Theory, 2010. doi:10.1007/978-3-642-16108-7_32

Markdown

[Zhdanov and Kalnishkan. "An Identity for Kernel Ridge Regression." International Conference on Algorithmic Learning Theory, 2010.](https://mlanthology.org/alt/2010/zhdanov2010alt-identity/) doi:10.1007/978-3-642-16108-7_32

BibTeX

@inproceedings{zhdanov2010alt-identity,
  title     = {{An Identity for Kernel Ridge Regression}},
  author    = {Zhdanov, Fedor and Kalnishkan, Yuri},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {2010},
  pages     = {405-419},
  doi       = {10.1007/978-3-642-16108-7_32},
  url       = {https://mlanthology.org/alt/2010/zhdanov2010alt-identity/}
}