Intransitive Likelihood-Ratio Classifiers

Abstract

In this work, we introduce an information-theoretic based correction term to the likelihood ratio classification method for multiple classes. Under certain conditions, the term is sufficient for optimally correcting the dif- ference between the true and estimated likelihood ratio, and we analyze this in the Gaussian case. We find that the new correction term signif- icantly improves the classification results when tested on medium vo- cabulary speech recognition tasks. Moreover, the addition of this term makes the class comparisons analogous to an intransitive game and we therefore use several tournament-like strategies to deal with this issue. We find that further small improvements are obtained by using an appro- priate tournament. Lastly, we find that intransitivity appears to be a good measure of classification confidence.

Cite

Text

Bilmes et al. "Intransitive Likelihood-Ratio Classifiers." Neural Information Processing Systems, 2001.

Markdown

[Bilmes et al. "Intransitive Likelihood-Ratio Classifiers." Neural Information Processing Systems, 2001.](https://mlanthology.org/neurips/2001/bilmes2001neurips-intransitive/)

BibTeX

@inproceedings{bilmes2001neurips-intransitive,
  title     = {{Intransitive Likelihood-Ratio Classifiers}},
  author    = {Bilmes, Jeff and Ji, Gang and Meila, Marina},
  booktitle = {Neural Information Processing Systems},
  year      = {2001},
  pages     = {1141-1148},
  url       = {https://mlanthology.org/neurips/2001/bilmes2001neurips-intransitive/}
}