A Rate-Distortion One-Class Model and Its Applications to Clustering
Abstract
We study the problem of one-class classification, in which we seek a rule to separate a coherent subset of instances similar to a few positive examples from a large pool of instances. We find that the problem can be formulated naturally in terms of a rate-distortion tradeoff, which can be analyzed precisely and leads to an efficient algorithm that competes well with two previous one-class methods. We also show that our model can be extended naturally to clustering problems in which it is important to remove background clutter to improve cluster purity.
Cite
Text
Crammer et al. "A Rate-Distortion One-Class Model and Its Applications to Clustering." International Conference on Machine Learning, 2008. doi:10.1145/1390156.1390180Markdown
[Crammer et al. "A Rate-Distortion One-Class Model and Its Applications to Clustering." International Conference on Machine Learning, 2008.](https://mlanthology.org/icml/2008/crammer2008icml-rate/) doi:10.1145/1390156.1390180BibTeX
@inproceedings{crammer2008icml-rate,
title = {{A Rate-Distortion One-Class Model and Its Applications to Clustering}},
author = {Crammer, Koby and Talukdar, Partha Pratim and Pereira, Fernando C. N.},
booktitle = {International Conference on Machine Learning},
year = {2008},
pages = {184-191},
doi = {10.1145/1390156.1390180},
url = {https://mlanthology.org/icml/2008/crammer2008icml-rate/}
}