Amari distance

Amari distance is a concept from information geometry and is used to measure the difference between two probability distributions. It is particularly relevant in the context of statistical inference and machine learning. The Amari distance is derived from the notion of the Bhattacharyya distance and employs the idea of the Fisher information metric. In a more formal sense, the Amari distance can be defined as a generalization of the Kullback-Leibler divergence.