Infinite-dimensional statistical manifolds based on a balanced chart
From MaRDI portal
Publication:265266
DOI10.3150/14-BEJ673zbMATH Open1388.60043arXiv1308.3602MaRDI QIDQ265266FDOQ265266
Authors: Nigel J. Newton
Publication date: 1 April 2016
Published in: Bernoulli (Search for Journal in Brave)
Abstract: We develop a family of infinite-dimensional Banach manifolds of measures on an abstract measurable space, employing charts that are "balanced" between the density and log-density functions. The manifolds, , retain many of the features of finite-dimensional information geometry; in particular, the -divergences are of class , enabling the definition of the Fisher metric and -derivatives of particular classes of vector fields. Manifolds of probability measures, , based on centred versions of the charts are shown to be -embedded submanifolds of the . The Fisher metric is a pseudo-Riemannian metric on . However, when restricted to finite-dimensional embedded submanifolds it becomes a Riemannian metric, allowing the full development of the geometry of -covariant derivatives. and provide natural settings for the study and comparison of approximations to posterior distributions in problems of Bayesian estimation.
Full work available at URL: https://arxiv.org/abs/1308.3602
Recommendations
- An infinite-dimensional statistical manifold modelled on Hilbert space
- Infinite-dimensional manifolds of finite-entropy probability measures
- Manifolds of differentiable densities
- A infinite-dimensional geometric structure on the space of all the probability measures equivalent to a given one
- scientific article; zbMATH DE number 44578
Foundations and philosophical topics in statistics (62A01) Geometric probability and stochastic geometry (60D05) Probability theory on algebraic and topological structures (60B99)
Cites Work
- Title not available (Why is that?)
- Title not available (Why is that?)
- Second order efficiency of minimum contrast estimators in a curved exponential family
- Approximate nonlinear filtering by projection on exponential manifolds of densities
- The exponential statistical manifold: mean parameters, orthogonality and space transformations
- A infinite-dimensional geometric structure on the space of all the probability measures equivalent to a given one
- Statistical manifold as an affine space: a functional equation approach
- Generalised Thermostatistics
- Title not available (Why is that?)
- Geometric science of information. First international conference, GSI 2013, Paris, France, August 28--30, 2013. Proceedings
- On \(\varphi \)-families of probability distributions
- Title not available (Why is that?)
- Title not available (Why is that?)
- Connections on Non-Parametric Statistical Manifolds by Orlicz Space Geometry
- Title not available (Why is that?)
- An infinite-dimensional statistical manifold modelled on Hilbert space
- Title not available (Why is that?)
- Infinite-dimensional manifolds of finite-entropy probability measures
- Exponential statistical manifold
- Dual connections in nonparametric classical information geometry
Cited In (9)
- Manifolds of differentiable densities
- A two-parameter family of non-parametric, deformed exponential manifolds
- An infinite-dimensional statistical manifold modelled on Hilbert space
- Infinite-dimensional manifolds of finite-entropy probability measures
- The Banach manifold of measures and the Lagrange multipliers of statistical mechanics
- A class of non-parametric statistical manifolds modelled on Sobolev space
- On some information geometric structures concerning mercator projections
- A class of non-parametric deformed exponential statistical models
- On Euclidean manifolds being a subspace of the space of probability measures with finite supports to a certain infinite compact set of dimension zero
This page was built for publication: Infinite-dimensional statistical manifolds based on a balanced chart
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q265266)