Neural Mutual Information Estimation with Vector Copulas
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908609053458432 |
|---|---|
| author | Chen, Yanzhi Ou, Zijing Weller, Adrian Gutmann, Michael U. |
| author_facet | Chen, Yanzhi Ou, Zijing Weller, Adrian Gutmann, Michael U. |
| contents | 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 estimator. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20968 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neural Mutual Information Estimation with Vector Copulas Chen, Yanzhi Ou, Zijing Weller, Adrian Gutmann, Michael U. Machine Learning 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 estimator. |
| title | Neural Mutual Information Estimation with Vector Copulas |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.20968 |