paper-with-me

홈 › Papers

Some results on a $χ$-divergence, an~extended~Fisher information and~generalized~Cramér-Rao inequalities

2013-05-27 · Jean-François Bercher

We propose a modified $\chi^{\beta}$-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 $q$-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.

📄 PDF Abstract BibTeX arXiv:1305.6213

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On some interrelations of generalized $q$-entropies and a generalized Fisher information, including a Cramér-Rao inequality

2013-05-27 · Jean-François Bercher

In this communication, we describe some interrelations between generalized $q$-entropies and a generalized version of Fisher information. In information theory, the de Bruijn identity links the Fisher information and the…

On Voronoi diagrams and dual Delaunay complexes on the information-geometric Cauchy manifolds

2020-06-12 · Frank Nielsen

We study the Voronoi diagrams of a finite set of Cauchy distributions and their dual complexes from the viewpoint of information geometry by considering the Fisher-Rao distance, the Kullback-Leibler divergence, the chi s…

Fisher Auto-Encoders

2020-07-12 · Khalil Elkhalil, Ali Hasan, Jie Ding, Sina Farsiu 외

It has been conjectured that the Fisher divergence is more robust to model uncertainty than the conventional Kullback-Leibler (KL) divergence. This motivates the design of a new class of robust generative auto-encoders (…

A numerical approximation method for the Fisher-Rao distance between multivariate normal distributions

2023-02-16 · Frank Nielsen

We present a simple method to approximate Rao's distance between multivariate normal distributions based on discretizing curves joining normal distributions and approximating Rao's distances between successive nearby nor…

von Mises-Fisher distributions and their statistical divergence

2022-02-10 · Toru Kitagawa, Jeff Rowley

The von Mises-Fisher family is a parametric family of distributions on the surface of the unit ball, summarised by a concentration parameter and a mean direction. As a quasi-Bayesian prior, the von Mises-Fisher distribut…