Mutual Information Estimation via Normalizing Flows

Abstract

We propose a novel approach to the problem of mutual information (MI) estimation via introducing a family of estimators based on normalizing flows. The estimator maps original data to the target distribution, for which MI is easier to estimate. We additionally explore the target distributions with known closed-form expressions for MI. Theoretical guarantees are provided to demonstrate that our approach yields MI estimates for the original data. Experiments with high-dimensional data are conducted to highlight the practical advantages of the proposed method.

Cite

Text

Butakov et al. "Mutual Information Estimation via Normalizing Flows." Neural Information Processing Systems, 2024. doi:10.52202/079017-0099

Markdown

[Butakov et al. "Mutual Information Estimation via Normalizing Flows." Neural Information Processing Systems, 2024.](https://mlanthology.org/neurips/2024/d2024neurips-mutual/) doi:10.52202/079017-0099

BibTeX

@inproceedings{d2024neurips-mutual,
  title     = {{Mutual Information Estimation via Normalizing Flows}},
  author    = {Butakov, I. D. and Tolmachev, A. D. and Malanchuk, S. V. and Neopryatnaya, A. M. and Frolov, A. A.},
  booktitle = {Neural Information Processing Systems},
  year      = {2024},
  doi       = {10.52202/079017-0099},
  url       = {https://mlanthology.org/neurips/2024/d2024neurips-mutual/}
}