Sparse Meta-Gaussian Information Bottleneck

Abstract

We present a new sparse compression technique based on the information bottleneck (IB) principle, which takes into account side information. This is achieved by introducing a sparse variant of IB which preserves the information in only a few selected dimensions of the original data through compression. By assuming a Gaussian copula we can capture arbitrary non-Gaussian margins, continuous or discrete. We apply our model to select a sparse number of biomarkers relevant to the evolution of malignant melanoma and show that our sparse selection provides reliable predictors.

Cite

Text

Rey et al. "Sparse Meta-Gaussian Information Bottleneck." International Conference on Machine Learning, 2014.

Markdown

[Rey et al. "Sparse Meta-Gaussian Information Bottleneck." International Conference on Machine Learning, 2014.](https://mlanthology.org/icml/2014/rey2014icml-sparse/)

BibTeX

@inproceedings{rey2014icml-sparse,
  title     = {{Sparse Meta-Gaussian Information Bottleneck}},
  author    = {Rey, Melani and Roth, Volker and Fuchs, Thomas},
  booktitle = {International Conference on Machine Learning},
  year      = {2014},
  pages     = {910-918},
  volume    = {32},
  url       = {https://mlanthology.org/icml/2014/rey2014icml-sparse/}
}