关于反向Pinsker不等式
On Reverse Pinsker Inequalities
摘要:
新的上界的相对熵推导出作为总变化距离的函数。一个界限是Verdú对一般概率测度的一个不等式的改进。第二个界限提高了由Csiszár和Talata的不等式的紧密性,用于定义在公共有限集上的任意概率测度。后一个结果被进一步推广,对于有限集上的概率测度,得到了任意非负阶(包括$\infty$)的Rényi散度作为总变差距离的函数的上界. Verdú关于总变差距离的另一个下界,用相对信息的分布来表示,被收紧,并且在一定条件下得到。这些改进的效果举例说明。
英文摘要:
New upper bounds on the relative entropy are derived as a function of the total variation distance. One bound refines an inequality by Verdú for general probability measures. A second bound improves the tightness of an inequality by Csiszár and Talata for arbitrary probability measures that are defined on a common finite set. The latter result is further extended, for probability measures on a finite set, leading to an upper bound on the Rényi divergence of an arbitrary non-negative order (including $\infty$) as a function of the total variation distance. Another lower bound by Verdú on the total variation distance, expressed in terms of the distribution of the relative information, is tightened and it is attained under some conditions. The effect of these improvements is exemplified.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。