ML Anthology

Absolute Error Bounds for Learning Linear Functions Online

Ethan Bernstein
COLT 1992 pp. 160-163
doi:10.1145/130385.130403 /colt/1992/bernstein1992colt-absolute/

Abstract

In this note, we consider the problem of learning a linear function from ** to ** online. Two previous algorithms have been presented which achieve an optimal sum of squared error terms. We show that neither algorithm performs well with respect to absolute error. We also show that in both problem settings, very simple ideas given an algorithm which achieves optimal or close to optimal worst case absolute error.

PDF COLT Semantic Scholar

Cite

Text

Bernstein. "Absolute Error Bounds for Learning Linear Functions Online." Annual Conference on Computational Learning Theory, 1992. doi:10.1145/130385.130403

Markdown

[Bernstein. "Absolute Error Bounds for Learning Linear Functions Online." Annual Conference on Computational Learning Theory, 1992.](https://mlanthology.org/colt/1992/bernstein1992colt-absolute/) doi:10.1145/130385.130403

BibTeX

@inproceedings{bernstein1992colt-absolute,
  title     = {{Absolute Error Bounds for Learning Linear Functions Online}},
  author    = {Bernstein, Ethan},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {1992},
  pages     = {160-163},
  doi       = {10.1145/130385.130403},
  url       = {https://mlanthology.org/colt/1992/bernstein1992colt-absolute/}
}