依赖性的两种度量
Two Measures of Dependence
摘要:
引入了两类随机变量间的相关测度。它们分别基于$α$阶的Rényi散度和相对$α$ -熵,并且当它们的阶数$α$为1时,这两种相关测度都归结为香农互信息.第一种测度与互信息互信息具有数据处理不等式等性质,并与复合假设检验中的最优误差指数有关。第二个度量不满足数据处理不等式,但在分布式任务编码的上下文中自然出现。
英文摘要:
Two families of dependence measures between random variables are introduced. They are based on the Rényi divergence of order $α$ and the relative $α$-entropy, respectively, and both dependence measures reduce to Shannon's mutual information when their order $α$ is one. The first measure shares many properties with the mutual information, including the data-processing inequality, and can be related to the optimal error exponents in composite hypothesis testing. The second measure does not satisfy the data-processing inequality, but appears naturally in the context of distributed task encoding.
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。