English

Manifolds of Differentiable Densities

Probability 2018-06-12 v3 Information Theory Differential Geometry Functional Analysis math.IT Statistics Theory Statistics Theory

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 CbkC_b^k with respect to appropriate reference measures. The case k=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 α\alpha-covariant derivatives for all αR\alpha\in R. By construction, they are CC^\infty-embedded submanifolds of particular manifolds of finite measures. The statistical manifolds are dually (α=±1\alpha=\pm 1) flat, and admit mixture and exponential representations as charts. Their curvatures with respect to the α\alpha-covariant derivatives are derived. The likelihood function associated with a finite sample is a continuous function on each of the manifolds, and the α\alpha-divergences are of class CC^\infty.

Keywords

Cite

@article{arxiv.1608.03979,
  title  = {Manifolds of Differentiable Densities},
  author = {Nigel J. Newton},
  journal= {arXiv preprint arXiv:1608.03979},
  year   = {2018}
}

Comments

Version 3: 27 pages. Introduction expanded to discuss applications. Concluding Remarks section added. Improved definition of tangent space (space of signed measures). Discussion of Bayesian data fusion expanded. Discussion of normal charts for the $\alpha$ covariant derivatives added. New references added. No change to results. To appear in ESAIM:Probability and Statistics www.esaim-ps.org

R2 v1 2026-06-22T15:19:03.986Z