arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1708.07211math.DG
收藏

概率测度的几何平均与Fisher信息度量的测地线

Geometric mean of probability measures and geodesics of Fisher information metric

Mitsuhiro Itoh, Hiroyasu Satoh

AI总结:

本文通过定义概率测度的几何平均,研究了Fisher信息度量下概率测度空间的信息几何,证明了任意两点间存在唯一测地线并给出了黎曼距离函数。

摘要:

在连通紧光滑流形$M$上具有正密度函数的所有概率测度的空间$\mathcal{P}(M)$承载着Fisher信息度量$G$。我们定义了概率测度的几何平均,并借助它研究装备了$G$的$\mathcal{P}(M)$的信息几何。我们证明,连接任意概率测度$μ_1$和$μ_2$的测地线段可以用其端点的归一化几何平均来表示。作为应用,我们证明$\mathcal{P}(M)$中的任意两点可由唯一测地线连接。此外,我们证明由$\ell(μ_1, μ_2):=2\arccos\int_M \sqrt{p_1\,p_2}\,dλ$(其中$μ_i=p_i\,λ$,$i=1,2$)定义的函数$\ell$给出了$\mathcal{P}(M)$上的黎曼距离函数。并证明所有测地线均是最短的。

英文摘要:

The space of all probability measures having positive density function on a connected compact smooth manifold $M$, denoted by $\mathcal{P}(M)$, carries the Fisher information metric $G$. We define the geometric mean of probability measures by the aid of which we investigate information geometry of $\mathcal{P}(M)$, equipped with $G$. We show that a geodesic segment joining arbitrary probability measures $μ_1$ and $μ_2$ is expressed by using the normalized geometric mean of its endpoints. As an application, we show that any two points of $\mathcal{P}(M)$ can be joined by a unique geodesic. Moreover, we prove that the function $\ell$ defined by $\ell(μ_1, μ_2):=2\arccos\int_M \sqrt{p_1\,p_2}\,dλ$, $μ_i=p_i\,λ$, $i=1,2$ gives the Riemannian distance function on $\mathcal{P}(M)$. It is shown that geodesics are all minimal.

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。

↑