Fisher Information inequalities and the Central Limit Theorem

Oliver Johnson, Andrew Barron

Published 2001-11-02, updated 2003-07-04Version 2

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.