Some Discriminant-Based PAC Algorithms

Abstract

A classical approach in multi-class pattern classification is the following. Estimate the probability distributions that generated the observations for each label class, and then label new instances by applying the Bayes classifier to the estimated distributions. That approach provides more useful information than just a class label; it also provides estimates of the conditional distribution of class labels, in situations where there is class overlap.

Cite

Text

Goldberg. "Some Discriminant-Based PAC Algorithms." Journal of Machine Learning Research, 2006.

Markdown

[Goldberg. "Some Discriminant-Based PAC Algorithms." Journal of Machine Learning Research, 2006.](https://mlanthology.org/jmlr/2006/goldberg2006jmlr-some/)

BibTeX

@article{goldberg2006jmlr-some,
  title     = {{Some Discriminant-Based PAC Algorithms}},
  author    = {Goldberg, Paul W.},
  journal   = {Journal of Machine Learning Research},
  year      = {2006},
  pages     = {283-306},
  volume    = {7},
  url       = {https://mlanthology.org/jmlr/2006/goldberg2006jmlr-some/}
}