On -Divergences: Integral Representations, Local Behavior, and Inequalities
arXiv:1804.06334 · doi:10.3390/e20050383
Abstract
This paper is focused on -divergences, consisting of three main contributions. The first one introduces integral representations of a general -divergence by means of the relative information spectrum. The second part provides a new approach for the derivation of -divergence inequalities, and it exemplifies their utility in the setup of Bayesian binary hypothesis testing. The last part of this paper further studies the local behavior of -divergences.
arXiv commentFinal edits before publication. To appear in the Entropy journal, special issue on Entropy and Information Inequalities, May 2018
References in corpus (5)
- Rényi Divergence and Kullback-Leibler Divergence
- -divergence Inequalities
- On Pinsker's Type Inequalities and Csiszar's f-divergences. Part I: Second and Fourth-Order Inequalities
- Log-Determinant Divergences Revisited: Alpha--Beta and Gamma Log-Det Divergences
- Tight Bounds for Symmetric Divergence Measures and a Refined Bound for Lossless Source Coding
Cited by in corpus (10)
- On a generalization of the Jensen-Shannon divergence
- Fusion of Probability Density Functions
- Minimax Robust Detection: Classic Results and Recent Advances
- On Relations Between the Relative entropy and -Divergence, Generalizations and Applications
- On Data-Processing and Majorization Inequalities for -Divergences with Applications
- Least th-Order and Rényi Generative Adversarial Networks
- The Differential Entropy of Mixtures: New Bounds and Applications
- Comparison of information criteria for detection of useful signal in noisy environment
- Infinite-dimensional gradient-based descent for alpha-divergence minimisation
- Information divergences and likelihood ratios of Poisson processes and point patterns