大阪大学　数理・データ科学教育研究センター
Center for Mathematical Modeling and Data Science,The University of Osaka

Neural Mutual Information Estimation with Vector Copulas

Michael U. Gutmann 先生

1. ホーム
2. セミナー・集中講義
3. セミナー
4. Neural Mutual Information Estimation with Vector Copulas

大阪大学 データ科学セミナーシリーズ 第66回

Neural Mutual Information Estimation with Vector Copulas

Michael U. Gutmann 先生

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.