Neural Mutual Information Estimation with Vector Copulas

Yanzhi Chen, Zijing Ou, Adrian Weller, Michael U. Gutmann

Keywords: mutual information, flow-based models, copulas, vector ranks

TL;DR: A mutual information estimator based on recent vector copula theory, which explicitly disentangles the marginal distributions and dependence structure in estimation.

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.

Primary Area: General machine learning (supervised, unsupervised, online, active, etc.)

Submission Number: 22482