ML Anthology

When Is Small Beautiful?

Amiran Ambroladze, John Shawe-Taylor
COLT 2003 pp. 729-730
doi:10.1007/978-3-540-45167-9_53 /colt/2003/ambroladze2003colt-small/

Abstract

The basic bound on the generalisation error of a PAC learner makes the assumption that a consistent hypothesis exists. This makes it appropriate to apply the method only in the case where we have a guarantee that a consistent hypothesis can be found, something that is rarely possible in real applications. The same problem arises if we decide not to use a hypothesis unless its error is below a prespecified number.

PDF COLT Semantic Scholar

Cite

Text

Ambroladze and Shawe-Taylor. "When Is Small Beautiful?." Annual Conference on Computational Learning Theory, 2003. doi:10.1007/978-3-540-45167-9_53

Markdown

[Ambroladze and Shawe-Taylor. "When Is Small Beautiful?." Annual Conference on Computational Learning Theory, 2003.](https://mlanthology.org/colt/2003/ambroladze2003colt-small/) doi:10.1007/978-3-540-45167-9_53

BibTeX

@inproceedings{ambroladze2003colt-small,
  title     = {{When Is Small Beautiful?}},
  author    = {Ambroladze, Amiran and Shawe-Taylor, John},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2003},
  pages     = {729-730},
  doi       = {10.1007/978-3-540-45167-9_53},
  url       = {https://mlanthology.org/colt/2003/ambroladze2003colt-small/}
}