ML Anthology

The Learning Complexity of Smooth Functions of a Single Variable

Don Kimber, Philip M. Long
COLT 1992 pp. 153-159
doi:10.1145/130385.130402 /colt/1992/kimber1992colt-learning/

Abstract

We study the on-line learning of classes of functions of a single real variable formed through bounds on various norms of functions' derivatives. We determine the best bounds obtainable on the worst-case sum of squared errors (also "absolute" errors) for several such classes.

PDF COLT Semantic Scholar

Cite

Text

Kimber and Long. "The Learning Complexity of Smooth Functions of a Single Variable." Annual Conference on Computational Learning Theory, 1992. doi:10.1145/130385.130402

Markdown

[Kimber and Long. "The Learning Complexity of Smooth Functions of a Single Variable." Annual Conference on Computational Learning Theory, 1992.](https://mlanthology.org/colt/1992/kimber1992colt-learning/) doi:10.1145/130385.130402

BibTeX

@inproceedings{kimber1992colt-learning,
  title     = {{The Learning Complexity of Smooth Functions of a Single Variable}},
  author    = {Kimber, Don and Long, Philip M.},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {1992},
  pages     = {153-159},
  doi       = {10.1145/130385.130402},
  url       = {https://mlanthology.org/colt/1992/kimber1992colt-learning/}
}