A family of statistical symmetric divergences based on Jensen's inequality

Abstract

We introduce a novel parametric family of symmetric information-theoretic distances based on Jensen's inequality for a convex functional generator. In particular, this family unifies the celebrated Jeffreys divergence with the Jensen-Shannon divergence when the Shannon entropy generator is chosen. We then design a generic algorithm to compute the unique centroid defined as the minimum average divergence. This yields a smooth family of centroids linking the Jeffreys to the Jensen-Shannon centroid. Finally, we report on our experimental results.

15 pages, 2 figure

References in corpus (1)

• The Burbea-Rao and Bhattacharyya centroids

Cited by in corpus (16)

• On a generalization of the Jensen-Shannon divergence and the JS-symmetrization of distances relying on abstract means
• The Optimal Arbitrary-Proportional Finite-Set-Partitioning
• Bootstrap Methods for the Empirical Study of Decision-Making and Information Flows in Social Systems
• Solving Bayesian Inverse Problems via Variational Autoencoders
• On the symmetrical Kullback-Leibler Jeffreys centroids
• Simulation of complex dynamics of mean-field $p$-spin models using measurement-based quantum feedback control
• Monte Carlo Information Geometry: The dually flat case
• On $w$-mixtures: Finite convex combinations of prescribed component distributions
• Jensen-Shannon Divergence and Non-linear Quantum Dynamics
• Self-supervised Representation Learning with Relative Predictive Coding
• Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification
• $\alpha$-Geodesical Skew Divergence
• On The Chain Rule Optimal Transport Distance
• Likelihood Ratio Exponential Families
• Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey
• Topic Modeling the Reading and Writing Behavior of Information Foragers