arXivDaily arXiv每日学术速递 周一至周五更新
arXiv math-ph/0104031math-phmath.DGmath.MP
收藏

非参数经典信息几何中的对偶联络

Dual Connections in Nonparametric Classical Information Geometry

M. R. Grasselli

摘要:

我们构造了一个无限维的信息流形指数Orlicz空间的基础上没有使用指数收敛的概念。然后,我们表明,凸混合物的概率密度位于同一连通分量的这个流形,并描述了一类密度,这种混合物可以扩展到一个开放的部分包含极值点。对于这个类,我们定义了一个无限维模拟的混合平行运输,并证明了它是对偶的指数平行运输相对于Fisher信息。我们还定义了α-导数,并证明了它们是极值(\pm 1)-导数的凸混合.

英文摘要:

We construct an infinite-dimensional information manifold based on exponential Orlicz spaces without using the notion of exponential convergence. We then show that convex mixtures of probability densities lie on the same connected component of this manifold, and characterize the class of densities for which this mixture can be extended to an open segment containing the extreme points. For this class, we define an infinite-dimensional analogue of the mixture parallel transport and prove that it is dual to the exponential parallel transport with respect to the Fisher information. We also define α-derivatives and prove that they are convex mixtures of the extremal (\pm 1)-derivatives.

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。

↑