Fisher Information inequalities and the Central Limit Theorem
arXiv:math/0111020 · doi:10.1007/s00440-004-0344-0
Abstract
We give conditions for an O(1/n) rate of convergence of Fisher information and relative entropy in the Central Limit Theorem. We use the theory of projections in L2 spaces and Poincare inequalities, to provide a better understanding of the decrease in Fisher information implied by results of Barron and Brown. We show that if the standardized Fisher information ever becomes finite then it converges to zero.
19 pages
Cited by in corpus (23)
- Generalized Entropy Power Inequalities and Monotonicity Properties of Information
- Information Theoretic Proofs of Entropy Power Inequalities
- Forward and Reverse Entropy Power Inequalities in Convex Geometry
- Rate of convergence and Edgeworth-type expansion in the entropic central limit theorem
- Compound Poisson Approximation via Information Functionals
- Entropy bounds on abelian groups and the Ruzsa divergence
- One-parameter class of uncertainty relations based on entropy power
- Integration by parts and representation of information functionals
- Combinatorial Entropy Power Inequalities: A Preliminary Study of the Stam region
- Monotonic Convergence in an Information-Theoretic Law of Small Numbers
- A stroll along the gamma
- Fisher information and convergence to stable laws
- Quantum Ruzsa Divergence to Quantify Magic
- IT formulae for gamma target: mutual information and relative entropy
- Entropy inequalities for stable densities and strengthened central limit theorems
- Superconvergence phenomenon in Wiener chaoses
- An information-theoretic Central Limit Theorem for finitely susceptible FKG systems
- Information-theoretic convergence of extreme values to the Gumbel distribution
- Entropy and thinning of discrete random variables
- Convergence of the Poincare Constant
- Rates of convergence for Renyi entropy in extreme value theory
- Towards Optimal Convergence Rates for the Quantum Central Limit Theorem
- Maximal correlation and the rate of Fisher information convergence in the Central Limit Theorem