$\alpha$-Geodesical Skew Divergence

Abstract

The asymmetric skew divergence smooths one of the distributions by mixing it, to a degree determined by the parameter $\lambda$, with the other distribution. Such divergence is an approximation of the KL divergence that does not require the target distribution to be absolutely continuous with respect to the source distribution. In this paper, an information geometric generalization of the skew divergence called the $\alpha$-geodesical skew divergence is proposed, and its properties are studied.

References in corpus (9)

• On a generalization of the Jensen-Shannon divergence and the JS-symmetrization of distances relying on abstract means
• Information Entropy, Information Distances and Complexity in Atoms
• On a generalization of the Jensen-Shannon divergence
• Quantum Skew Divergence
• A family of statistical symmetric divergences based on Jensen's inequality
• Generalized Bhattacharyya and Chernoff upper bounds on Bayes error using quasi-arithmetic means
• On a Variational Definition for the Jensen-Shannon Symmetrization of Distances based on the Information Radius
• On the symmetrical Kullback-Leibler Jeffreys centroids
• Annealed Importance Sampling with q-Paths

Cited by in corpus (1)

• Information Geometrically Generalized Covariate Shift Adaptation