线性统计约束下的相对$α$ -熵极小
Relative $α$-Entropy Minimizers Subject to Linear Statistical Constraints
摘要:
我们研究的相对熵,称为相对$α$ -熵(表示$\mathscr{I}_α(P,Q)$)的参数家庭的最小化。当考虑压缩长度的累积量而不是预期的压缩长度时,这些作为不匹配压缩下的冗余而出现。这些参数相对熵是通常相对熵(Kullback-Leibler发散)的推广。就像相对熵一样,这些相对$α$ -熵表现得像平方欧几里德距离,并满足毕达哥拉斯性质。研究了构成一个线性族的概率分布集上第一个参数上的$\mathscr{I}_α(P,Q)$的极小化问题。这样的最小化推广了最大雷尼或察利斯熵原理。线性族的最小化概率分布(称为$\mathscr{I}_α$ -投影)具有幂律。
英文摘要:
We study minimization of a parametric family of relative entropies, termed relative $α$-entropies (denoted $\mathscr{I}_α(P,Q)$). These arise as redundancies under mismatched compression when cumulants of compressed lengths are considered instead of expected compressed lengths. These parametric relative entropies are a generalization of the usual relative entropy (Kullback-Leibler divergence). Just like relative entropy, these relative $α$-entropies behave like squared Euclidean distance and satisfy the Pythagorean property. Minimization of $\mathscr{I}_α(P,Q)$ over the first argument on a set of probability distributions that constitutes a linear family is studied. Such a minimization generalizes the maximum Rényi or Tsallis entropy principle. The minimizing probability distribution (termed $\mathscr{I}_α$-projection) for a linear family is shown to have a power-law.
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。