Some results on a $\chi$-divergence, an~extended~Fisher information and~generalized~Cram\'er-Rao inequalities
Jean-Fran\c{c}ois Bercher (LIGM)

TL;DR
This paper introduces a modified chi-divergence and a generalized Fisher information, leading to extended Cramér-Rao inequalities and new characterizations of generalized q-Gaussians, with potential implications for uncertainty relations.
Contribution
It proposes a new chi-divergence, defines a generalized Fisher information, and extends classical inequalities and characterizations in statistical estimation theory.
Findings
Introduces a modified chi-divergence with new properties.
Develops generalized Cramér-Rao inequalities involving the new Fisher information.
Provides new characterizations of generalized q-Gaussians and potential uncertainty relations.
Abstract
We propose a modified -divergence, give some of its properties, and show that this leads to the definition of a generalized Fisher information. We give generalized Cram\'er-Rao inequalities, involving this Fisher information, an extension of the Fisher information matrix, and arbitrary norms and power of the estimation error. In the case of a location parameter, we obtain new characterizations of the generalized -Gaussians, for instance as the distribution with a given moment that minimizes the generalized Fisher information. Finally we indicate how the generalized Fisher information can lead to new uncertainty relations.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsStatistical Mechanics and Entropy · Mathematical Inequalities and Applications · Distributed Sensor Networks and Detection Algorithms
