Optimal guessing under nonextensive framework and associated moment bounds

DOI10.1016/J.SPL.2023.109812zbMATH Open1515.60029arXiv1905.07729OpenAlexW2946631950MaRDI QIDQ6165367FDOQ6165367

Abhik Ghosh

Publication date: 4 July 2023

Published in: Statistics \& Probability Letters (Search for Journal in Brave)

Abstract: We consider the problem of guessing the realization of a random variable but under more general Tsallis' non-extensive entropic framework rather than the classical Maxwell-Boltzman-Gibbs-Shannon framework. We consider both the conditional guessing problem in the presence of some related side information, and the unconditional one where no such side-information is available. For both types of the problem, the non-extensive moment bounds of the required number of guesses are derived; here we use the $q$-normalized expectation in place of the usual (linear) expectation to define the non-extensive moments. These moment bounds are seen to be a function of the logarithmic norm entropy measure, a recently developed two-parameter generalization of the Renyi entropy, and hence provide their information theoretic interpretation. We have also considered the case of uncertain source distribution and derived the non-extensive moment bounds for the corresponding mismatched guessing function. These mismatched bounds are interestingly seen to be linked with an important robust statistical divergence family known as the relative $$-entropies; similar link is discussed between the optimum mismatched guessing with the extremes of these relative entropy measures.

Full work available at URL: https://arxiv.org/abs/1905.07729

zbMATH Keywords

logarithmic super divergence\(q\)-normalized expectationlogarithmic norm entropyrelative \((\alpha, \beta)\)-entropyuncertain source

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Measures of information, entropy (94A17) Foundations of probability theory (60A99)

Cites Work

• On Information and Sufficiency
• A Mathematical Theory of Communication
• Possible generalization of Boltzmann-Gibbs statistics.
• Title not available (Why is that?)
• Generalization of Shannon–Khinchin Axioms to Nonextensive Systems and the Uniqueness Theorem for the Nonextensive Entropy
• Introduction to Nonextensive Statistical Mechanics
• A possible extension of Shannon's information theory
• Information gain within nonextensive thermostatistics
• Asymptotically scale-invariant occupancy of phase space makes the entropy S _q extensive
• Title not available (Why is that?)
• Complexity through nonextensivity
• Source coding with escort distributions and Rényi entropy bounds
• Minimization Problems Based on Relative <inline-formula> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula>-Entropy I: Forward Projection
• Nonextensive information theoretic kernels on measures
• Source coding theorem based on a nonadditive information content
• An inequality on guessing and its application to sequential decoding
• The logarithmic super divergence and asymptotic inference properties
• Guessing Under Source Uncertainty
• A Scale-Invariant Generalization of the Rényi Entropy, Associated Divergences and Their Optimizations Under Tsallis’ Nonextensive Framework

Cited In (2)

• Optimally and computations for relative surprise inferences
• Bounds on entropy in a guessing game

   Recommendations

• Estimation of arithmetic means and their applications in guessing theory 👍 👎
• Title not available (Why is that?) 👍 👎
• Bounds on entropy in a guessing game 👍 👎
• Guessing Under Source Uncertainty 👍 👎
• Title not available (Why is that?) 👍 👎

This page was built for publication: Optimal guessing under nonextensive framework and associated moment bounds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6165367)