Agglomerative Multivariate Information Bottleneck

Abstract

The information bottleneck method is an unsupervised model independent data organization technique. Given a joint distribution peA, B), this method con(cid:173) structs a new variable T that extracts partitions, or clusters, over the values of A that are informative about B. In a recent paper, we introduced a general princi(cid:173) pled framework for multivariate extensions of the information bottleneck method that allows us to consider multiple systems of data partitions that are inter-related. In this paper, we present a new family of simple agglomerative algorithms to construct such systems of inter-related clusters. We analyze the behavior of these algorithms and apply them to several real-life datasets.

Cite

Text

Slonim et al. "Agglomerative Multivariate Information Bottleneck." Neural Information Processing Systems, 2001.

Markdown

[Slonim et al. "Agglomerative Multivariate Information Bottleneck." Neural Information Processing Systems, 2001.](https://mlanthology.org/neurips/2001/slonim2001neurips-agglomerative/)

BibTeX

@inproceedings{slonim2001neurips-agglomerative,
  title     = {{Agglomerative Multivariate Information Bottleneck}},
  author    = {Slonim, Noam and Friedman, Nir and Tishby, Naftali},
  booktitle = {Neural Information Processing Systems},
  year      = {2001},
  pages     = {929-936},
  url       = {https://mlanthology.org/neurips/2001/slonim2001neurips-agglomerative/}
}