ML Anthology

Unlabeled Compression Schemes for Maximum Classes,

Dima Kuzmin, Manfred K. Warmuth
COLT 2005 pp. 591-605
doi:10.1007/11503415_40 /colt/2005/kuzmin2005colt-unlabeled/

Abstract

We give a compression scheme for any maximum class of VC dimension d that compresses any sample consistent with a concept in the class to at most d unlabeled points from the domain of the sample.

PDF COLT Semantic Scholar

Cite

Text

Kuzmin and Warmuth. "Unlabeled Compression Schemes for Maximum Classes, ." Annual Conference on Computational Learning Theory, 2005. doi:10.1007/11503415_40

Markdown

[Kuzmin and Warmuth. "Unlabeled Compression Schemes for Maximum Classes, ." Annual Conference on Computational Learning Theory, 2005.](https://mlanthology.org/colt/2005/kuzmin2005colt-unlabeled/) doi:10.1007/11503415_40

BibTeX

@inproceedings{kuzmin2005colt-unlabeled,
  title     = {{Unlabeled Compression Schemes for Maximum Classes, }},
  author    = {Kuzmin, Dima and Warmuth, Manfred K.},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2005},
  pages     = {591-605},
  doi       = {10.1007/11503415_40},
  url       = {https://mlanthology.org/colt/2005/kuzmin2005colt-unlabeled/}
}