Skip to content
Preprint

A two-point approach to the inverse problem in information geometry

Aug 2026 · 0 citations · 51 references
Mathematics

Abstract

We formulate the inverse problem in information geometry within a two-point tensorial framework and solve it for general metric-affine manifolds, without imposing any curvature or torsion constraints. The construction is explicit and starts directly from the given geometric data: the metric tensor is paired to the affine structure, realized through a local parallelism obtained from parallel transport. This yields a contrast bi-form inducing the original metric-affine manifold. The inverse problems for statistical manifolds admitting torsion and for statistical manifolds are then recovered by homotopical reduction. In this way, suitable pre-contrast and contrast functions are obtained, including several established constructions for statistical manifolds and SMATs. We apply the general theory to reductive homogeneous pseudo-Riemannian manifolds endowed with invariant affine connections. Particular attention is devoted to semisimple Lie groups with Cartan-Schouten connections and to odd-dimensional spheres equipped with Berger metrics.

View source

Similar papers

Open access Sep 2026

Riemannian vs. Lorentzian Geometry: A Multilevel Comparison

We present a comparative exposition of Riemannian and Lorentzian geometries, organized through successive levels of increasing structure. Beginning with scalar products on vector spaces, we proceed through smooth manifolds, left-invariant metrics on Lie groups, homogeneous spaces and contact metric geometry. At each le...

Giovanni Calvaruso, Maria Letizia Russo · 0 citations
Preprint Aug 2026

Invariant connections in geometric mechanics: reduction, nonlocality, and curvature effects

We present a systematic study on the role of invariant connections in geometric mechanics. We first develop a comprehensive theory of reduction under left- and right-invariant connections on Lie groups, showing that the Euler--Poincar\'e and Lie--Poisson equations are independent of the connection. We then introduce a...

Huang Qiao · 0 citations
Preprint Oct 2026

Gravity and generalised geometry from a Lie 2-algebroid perspective

We revisit the problem of defining natural torsion and curvature tensors for generalised connections and of using them to reconstruct the effective action for the massless modes of the closed string from generalised geometry. The starting point is the description of a Courant algebroid as a differential graded (dg) sym...

A. Chatzistavrakidis, Chris Hull, L. Jonke et al. · 0 citations
Preprint Aug 2026

A Cartan geometry from a correspondence space in Riemannian geometry

Cartan geometries are curved analogues of homogeneous spaces, and the correspondence space construction produces, from a Cartan geometry of one type, another of a different type over a larger base manifold. The unit tangent bundle of a Riemannian manifold is, in this language, a Cartan geometry of type $(\operatorname{...

Rodrigo Morón, Francisco J. Palomo · 0 citations
Preprint Aug 2026

Semilinear overdetermined problems, a divergence formula, and geometric inequalities

Considering an $n$-dimensional compact Riemannian manifold with a boundary that satisfies a Serrin-type problem, we prove sharp upper and lower bounds for the area of such a boundary. Then, we present the main result of this paper: a divergence formula for a special vector field on a given Riemannian manifold. This div...

B. Leandro, I. Menezes, R. Novais · 0 citations
Preprint Aug 2026

Connecting Riemannian Geometry and Statistical Inference for Correlation Matrices

The quotient-affine metric gives an intrinsic Riemannian geometry to full-rank correlation matrices, but its geodesic distance has no closed form and we are not aware of an analytic asymptotic null distribution for it. We connect this geometry, introduced in 2019, with Jennrich's 1970 asymptotic test for equality of co...

A. Kuketayev · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.