On a Variational Definition for the Jensen-Shannon Symmetrization of Distances based on the Information Radius

Abstract

We generalize the Jensen-Shannon divergence by considering a variational definition with respect to a generic mean extending thereby the notion of Sibson's information radius. The variational definition applies to any arbitrary distance and yields another way to define a Jensen-Shannon symmetrization of distances. When the variational optimization is further constrained to belong to prescribed probability measure families, we get relative Jensen-Shannon divergences and symmetrizations which generalize the concept of information projections. Finally, we discuss applications of these variational Jensen-Shannon divergences and diversity indices to clustering and quantization tasks of probability measures including statistical mixtures.

arXiv comment28 pages, 2 figures

References in corpus (9)

• Rényi Divergence and Kullback-Leibler Divergence
• On a generalization of the Jensen-Shannon divergence and the JS-symmetrization of distances relying on abstract means
• The Burbea-Rao and Bhattacharyya centroids
• On a generalization of the Jensen-Shannon divergence
• On the Chi square and higher-order Chi distances for approximating f-divergences
• Chernoff information of exponential families
• The metric property of the quantum Jensen-Shannon divergence
• Generalized Bhattacharyya and Chernoff upper bounds on Bayes error using quasi-arithmetic means
• On Approximating the Riemannian 1-Center

Cited by in corpus (4)

• The duo Bregman and Fenchel-Young divergences
• Revisiting Chernoff Information with Likelihood Ratio Exponential Families
• Evolving Network Modeling Driven by the Degree Increase and Decrease Mechanism
• $\alpha$-Geodesical Skew Divergence