齐次和空间非齐次F-发散的度量性质
Metric properties of homogeneous and spatially inhomogeneous F-divergences
摘要:
在本文中,我调查的建设和所谓的边际透视成本$H$,一个功能有关的最优熵运输问题得到的最小化过程,涉及成本函数$c$和熵函数的性质。在对应于选择$c=0$的纯熵情况下,函数$H$自然产生对称发散。我考虑各种熵的例子,我计算诱导边际透视函数,其中包括一些著名的泛函,如海林格距离,詹森-香农发散和Kullback-Liebler发散。我讨论这些功能的度量性质,我强调的重要作用,所谓的Matusita分歧。在熵-输运情形下,从功率熵$F_p(s)=(s^p-p(s-1)-1)/(p(p-1))$和成本$c=d^2$出发,证明了对于每个$d$,诱导的边际透视成本$H_p$是相应锥空间上度量的平方.
英文摘要:
In this paper I investigate the construction and the properties of the so-called marginal perspective cost $H$, a function related to Optimal Entropy-Transport problems obtained by a minimizing procedure, involving a cost function $c$ and an entropy function. In the pure entropic case, which corresponds to the choice $c=0$, the function $H$ naturally produces a symmetric divergence. I consider various examples of entropies and I compute the induced marginal perspective function, which includes some well-known functionals like the Hellinger distance, the Jensen-Shannon divergence and the Kullback-Liebler divergence. I discuss the metric properties of these functions and I highlight the important role of the so-called Matusita divergences. In the entropy-transport case, starting from the power like entropy $F_p(s)=(s^p-p(s-1)-1)/(p(p-1))$ and the cost $c=d^2$ for a given metric $d$, the main result of the paper ensures that for every $p>1$ the induced marginal perspective cost $H_p$ is the square of a metric on the corresponding cone space.
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。