有向信息的变分不等式及其应用
Variational Equalities of Directed Information and Applications
摘要:
本文引入了两个有向信息的变分等式,它们类似于Blahut-Arimoto算法(BAA)中的互信息的变分等式。随后,我们引入了非预期的率失真函数(RDF)${R}^{na}_{0,n}(D)$定义通过在[1]中引入的有向信息,我们建立了它的等价性Gorbunov-Pinsker的非预期的$ε$-熵$R^{\varepsilon}_{0,n}(D)$。通过引用某些结果,我们首先建立了${R}^{na}_{0,n}(D)$的无穷再生分布的存在性,然后给出了它在平稳情形下的隐式形式.最后,利用变分不等式和最优再生分布的封闭形式给出了计算${R}^{na}_{0,n}(D)$的算法.
英文摘要:
In this paper we introduce two variational equalities of directed information, which are analogous to those of mutual information employed in the Blahut-Arimoto Algorithm (BAA). Subsequently, we introduce nonanticipative Rate Distortion Function (RDF) ${R}^{na}_{0,n}(D)$ defined via directed information introduced in [1], and we establish its equivalence to Gorbunov-Pinsker's nonanticipatory $ε$-entropy $R^{\varepsilon}_{0,n}(D)$. By invoking certain results we first establish existence of the infimizing reproduction distribution for ${R}^{na}_{0,n}(D)$, and then we give its implicit form for the stationary case. Finally, we utilize one of the variational equalities and the closed form expression of the optimal reproduction distribution to provide an algorithm for the computation of ${R}^{na}_{0,n}(D)$.
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。