相对熵到计数向量的推广及其集中性质
A Generalization of Relative Entropy to Count Vectors and its Concentration Property
AI总结:
本文提出相对熵对和大于1的非负向量的新推广,在纯组合与概率设定下证明并精确量化了凸多面体线性约束下的集中现象,同时改进对偶化、ℓ∞距离集中性及与广义KL散度的关系,并推广到一般紧凸集。
摘要:
我们引入相对熵对和大于1的非负向量的一种新推广。我们在纯组合设定中、不涉及任何概率考虑的情况下证明:在定义凸多面体的线性约束存在时,这种广义相对熵会出现集中现象,并且我们精确量化了该集中程度。我们还给出了概率表述,并将集中结果推广到该表述。此外,我们对之前的工作提供了若干简化和改进,特别是在优化问题的对偶化、关于ℓ∞距离的集中性以及与广义KL散度的关系方面。我们的若干结果适用于一般紧凸集,而不一定是多面体。
英文摘要:
We introduce a new generalization of relative entropy to non-negative vectors with sums $\gt 1$. We show in a purely combinatorial setting, with no probabilistic considerations, that in the presence of linear constraints defining a convex polytope, a concentration phenomenon arises for this generalized relative entropy, and we quantify the concentration precisely. We also present a probabilistic formulation, and extend the concentration results to it. In addition, we provide a number of simplifications and improvements to our previous work, notably in dualizing the optimization problem, in the concentration with respect to $\ell_{\infty}$ distance, and in the relationship to generalized KL-divergence. A number of our results apply to general compact convex sets, not necessarily polyhedral.
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。