Maximal Correlation and the Rate of Fisher Information Convergence in the Central Limit Theorem

DOI10.1109/TIT.2020.2985957MaRDI QIDQ5124480zbMATH OpenOpenAlexFDO

Authors

Publication date 29 September 2020

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1905.11913

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Measures of information, entropy (94A17)

Abstract: We consider the behaviour of the Fisher information of scaled sums of independent and identically distributed random variables in the Central Limit Theorem regime. We show how this behaviour can be related to the second-largest non-trivial eigenvalue associated with the Hirschfeld--Gebelein--R'{e}nyi maximal correlation. We prove that assuming this eigenvalue satisfies a strict inequality, an $O(1/n)$ rate of convergence and a strengthened form of monotonicity hold.

Cited in

(7)

• Fisher information inequalities and the central limit theorem
• Maximal correlation and monotonicity of free entropy and of Stein discrepancy
• Information-theoretic convergence of extreme values to the Gumbel distribution
• Rates of Fisher information convergence in the central limit theorem for nonlinear statistics
• Fisher information bounds and applications to SDEs with small noise
• Total variation bounds in the Lindeberg central limit theorem
• Entropic conditional central limit theorem and Hadamard compression

This page was built for publication: Maximal Correlation and the Rate of Fisher Information Convergence in the Central Limit Theorem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5124480)