Estimating Mutual Information (MI), a key measure of dependence of random quantities without specific modelling assumptions, is a challenging problem in high dimensions. We propose a novel mutual information estimator based on parametrizing conditional densities using normalizing flows, a deep generative model that has gained popularity in recent years. This estimator leverages a block autoregressive structure to achieve improved bias-variance trade-offs on standard benchmark tasks.

翻译：互信息（MI）是一种无需特定建模假设、用于衡量随机变量间依赖性的关键指标，其在高维空间中的估计是一个具有挑战性的问题。本文提出一种新颖的互信息估计器，其核心在于利用归一化流——一种近年来备受关注的深度生成模型——对条件概率密度进行参数化。该估计器通过采用块自回归结构，在标准基准任务上实现了偏差-方差权衡的优化。