pith. sign in

arxiv: 1608.03979 · v3 · pith:L6LXFZVCnew · submitted 2016-08-13 · 🧮 math.PR · cs.IT· math.DG· math.FA· math.IT· math.ST· stat.TH

Manifolds of Differentiable Densities

classification 🧮 math.PR cs.ITmath.DGmath.FAmath.ITmath.STstat.TH
keywords manifoldsalphainftymeasuresadmitclasscovariantdensities
0
0 comments X
read the original abstract

We develop a family of infinite-dimensional (non-parametric) manifolds of probability measures. The latter are defined on underlying Banach spaces, and have densities of class $C_b^k$ with respect to appropriate reference measures. The case $k=\infty$, in which the manifolds are modelled on Fr\'{e}chet spaces, is included. The manifolds admit the Fisher-Rao metric and, unusually for the non-parametric setting, Amari's $\alpha$-covariant derivatives for all $\alpha\in R$. By construction, they are $C^\infty$-embedded submanifolds of particular manifolds of finite measures. The statistical manifolds are dually ($\alpha=\pm 1$) flat, and admit mixture and exponential representations as charts. Their curvatures with respect to the $\alpha$-covariant derivatives are derived. The likelihood function associated with a finite sample is a continuous function on each of the manifolds, and the $\alpha$-divergences are of class $C^\infty$.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.