Entropic Conditional Central Limit Theorem and Hadamard Compression

Autor:	Ma, Zhi-Ming, Yao, Liu-Quan, Yuan, Shuai, Zhang, Hua-Zi
Rok vydání:	2024
Předmět:	Mathematics - Probability Computer Science - Information Theory 60F05 28D20 68P30 94A17 62B10 94A29
Druh dokumentu:	Working Paper
Popis:	We make use of an entropic property to establish a convergence theorem (Main Theorem), which reveals that the conditional entropy measures the asymptotic Gaussianity. As an application, we establish the {\it entropic conditional central limit theorem} (CCLT), which is stronger than the classical CCLT. As another application, we show that continuous input under iterated Hadamard transform, almost every distribution of the output conditional on the values of the previous signals will tend to Gaussian, and the conditional distribution is in fact insensitive to the condition. The results enable us to make a theoretic study concerning Hadamard compression, which provides a solid theoretical analysis supporting the simulation results in previous literature. We show also that the conditional Fisher information can be used to measure the asymptotic Gaussianity. Comment: 40 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2401.11383 Zobrazit plný text záznamu View this record from Arxiv