NeurIPS 2025poster0 citations
Neural Mutual Information Estimation with Vector Copulas
Yanzhi Chen, Zijing Ou, Adrian Weller, Michael U. Gutmann
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.
mutual informationflow-based modelscopulasvector ranks
BibTeX
@inproceedings{
chen2025neural,
title={Neural Mutual Information Estimation with Vector Copulas},
author={Yanzhi Chen and Zijing Ou and Adrian Weller and Michael U. Gutmann},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=FYbe7r0mxu}
}