Neural Mutual Information Estimation with Vector Copulas
Abstract
Estimating mutual information (MI) is a fundamental task in data science and machine learning. Existing estimators mainly rely on either highly flexible models (e.g., neural networks), which require large amounts of data, or overly simplified models (e.g., Gaussian copula), which fail to capture complex distributions. Drawing upon recent vector copula theory, we propose a principled interpolation between these two extremes to achieve a better trade-off between complexity and capacity. Experiments on state-of-the-art synthetic benchmarks and real-world data with diverse modalities demonstrate the advantages of the proposed method.
Cite
Text
Chen et al. "Neural Mutual Information Estimation with Vector Copulas." Advances in Neural Information Processing Systems, 2025.Markdown
[Chen et al. "Neural Mutual Information Estimation with Vector Copulas." Advances in Neural Information Processing Systems, 2025.](https://mlanthology.org/neurips/2025/chen2025neurips-neural/)BibTeX
@inproceedings{chen2025neurips-neural,
title = {{Neural Mutual Information Estimation with Vector Copulas}},
author = {Chen, Yanzhi and Ou, Zijing and Weller, Adrian and Gutmann, Michael U.},
booktitle = {Advances in Neural Information Processing Systems},
year = {2025},
url = {https://mlanthology.org/neurips/2025/chen2025neurips-neural/}
}