Dual connections in nonparametric classical information geometry
From MaRDI portal
Abstract: 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 {alpha}-derivatives and prove that they are convex mixtures of the extremal (pm 1)-derivatives.
Recommendations
- Nonparametric information geometry: from divergence function to referential-representational biduality on statistical manifolds
- Nonparametric information geometry
- Connections on Non-Parametric Statistical Manifolds by Orlicz Space Geometry
- scientific article; zbMATH DE number 1302144
- Manifolds of differentiable densities
Cites work
- scientific article; zbMATH DE number 50401 (Why is no real title available?)
- scientific article; zbMATH DE number 3502574 (Why is no real title available?)
- scientific article; zbMATH DE number 713322 (Why is no real title available?)
- scientific article; zbMATH DE number 1055955 (Why is no real title available?)
- scientific article; zbMATH DE number 1560711 (Why is no real title available?)
- scientific article; zbMATH DE number 217456 (Why is no real title available?)
- scientific article; zbMATH DE number 2095985 (Why is no real title available?)
- scientific article; zbMATH DE number 2095988 (Why is no real title available?)
- scientific article; zbMATH DE number 3106666 (Why is no real title available?)
- A infinite-dimensional geometric structure on the space of all the probability measures equivalent to a given one
- An invariant form for the prior probability in estimation problems
- CONNECTIONS ON STATISTICAL MANIFOLDS OF DENSITY OPERATORS BY GEOMETRY OF NONCOMMUTATIVE Lp-SPACES
- Connections on Non-Parametric Statistical Manifolds by Orlicz Space Geometry
- Defining the curvature of a statistical problem (with applications to second order efficiency)
- Differential-geometrical methods in statistics
- The exponential statistical manifold: mean parameters, orthogonality and space transformations
Cited in
(16)- Variational representations of annealing paths: Bregman information under monotonic embedding
- Infinite-dimensional statistical manifolds based on a balanced chart
- On -families of probability distributions
- Geometry of EM and related iterative algorithms
- The exponential Orlicz space in quantum information geometry
- An infinite-dimensional statistical manifold modelled on Hilbert space
- Examples of the application of nonparametric information geometry to statistical physics
- Nonparametric information geometry: from divergence function to referential-representational biduality on statistical manifolds
- Exponential statistical manifold
- Sub-exponentiality in statistical exponential models
- Hydrodynamics in an external field
- Information-geometric measures for estimation of connection weight under correlated inputs
- Statistical manifold as an affine space: a functional equation approach
- Nonparametric information geometry
- A construction of a nonparametric quantum information manifold
- Information geometry of modal linear regression
This page was built for publication: Dual connections in nonparametric classical information geometry
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q907022)
