Conditional Shannon, Réyni, and Tsallis entropies estimation and asymptotic limits: discrete case

2020/02/16 by Diadie, Ba Amadou, Samb, Lo Gane
#FOS: Computer and information sciences #FOS: Mathematics #Methodology (stat.ME) #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.2002.06516

Abstract

A method of estimating the joint probability mass function of a pair of discrete random variables is described. This estimator is used to construct the conditional Shannon-Réyni-Tsallis entropies estimates. From there almost sure rates of convergence and asymptotic normality are established. The theorical results are validated by simulations.

Related

• Non parametric estimation of joint, Renyi-Stallis entropies and mutual\n information and asymptotic limits
• Entropies and their Asymptotic Theory in the discrete case
• Statistical Estimation of Conditional Shannon Entropy
• Asymptotic behaviour of weighted differential entropies in a Bayesian problem
• Tight Bounds on the R 'enyi Entropy via Majorization with Applications\n to Guessing and Compression