Ben Poole, Sherjil Ozair, Aaron van den Oord, Alexander A. Alemi, George Tucker
TL;DR本文提供了通用的、数据无关的 Mutual Information 估计方法，其中包括新的下限估计器。通过实验测试我们的方法在高维问题中具有强大的表现，特别是在变量之间存在非线性关系时。
Abstract
Estimating and optimizing mutual information (MI) is core to many problems in machine learning; however, bounding MI in high dimensions is challenging. To establish tractable and scalable objectives, recent work