Information geometry and sufficient statistics

DOI10.1007/s00440-014-0574-8zbMath1321.62008arXiv1207.6736OpenAlexW3098034875MaRDI QIDQ2349150

Nihat Ay, Le Hong Van, Juergen Jost, Lorenz J. Schwachhöfer

Publication date: 19 June 2015

Published in: Probability Theory and Related Fields (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1207.6736

zbMATH Keywords

sufficient statisticAmari-Chentsov tensorFisher quadratic formChentsov theorem

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Local Riemannian geometry (53B20) Sufficient statistics and fields (62B05)

Related Items

Examples of the application of nonparametric information geometry to statistical physics ⋮ Information geometry formalism for the spatially homogeneous Boltzmann equation ⋮ Information geometry on the curved \(q\)-exponential family with application to survival data analysis ⋮ The Markowitz Category ⋮ Geometry on degradation models and mis-specification analysis by using \(\alpha\)-divergence ⋮ On geodesic completeness for Riemannian metrics on smooth probability densities ⋮ The uniqueness of the Fisher metric as information metric ⋮ On the relation between geometrical quantum mechanics and information geometry ⋮ Quantum information geometry of driven CFTs ⋮ Information geometry, Jordan algebras, and a coadjoint orbit-like construction ⋮ The Kähler geometry of certain optimal transport problems ⋮ Fisher-Rao Riemannian geometry of equivalent Gaussian measures on Hilbert space ⋮ Hommage to Chentsov's theorem ⋮ Natural differentiable structures on statistical models and the Fisher metric ⋮ Parametric models and information geometry on \(W^\star\)-algebras ⋮ The geometric structure on a degradation model with application to optimal design under a cost constraint ⋮ The Fisher-Rao loss for learning under label noise ⋮ Quantum enhanced metrology of Hamiltonian parameters beyond the Cramèr–Rao bound ⋮ The \(L^p\)-Fisher-Rao metric and Amari-Čencov \(\alpha\)-connections ⋮ Designing universal causal deep learning models: The geometric (Hyper)transformer ⋮ An interpolating distance between optimal transport and Fisher-Rao metrics ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Manifolds of differentiable densities ⋮ Chentsov's theorem for exponential families ⋮ Semi-invariant Riemannian metrics in hydrodynamics ⋮ Statistical mirror symmetry ⋮ Fisher-Rao geometry of Dirichlet distributions ⋮ Amari-Chentsov structure on the statistical manifold of models for accelerated life tests ⋮ Manifolds of classical probability distributions and quantum density operators in infinite dimensions ⋮ A class of non-parametric statistical manifolds modelled on Sobolev space ⋮ Invariant metric under deformed Markov embeddings with overlapped supports ⋮ Uniqueness of the Fisher–Rao metric on the space of smooth densities ⋮ Warped Riemannian Metrics for Location-Scale Models ⋮ Geometry on the statistical manifold induced by the degradation model with soft failure data ⋮ From Hessian to Weitzenböck: manifolds with torsion-carrying connections ⋮ Nonparametric Estimations and the Diffeological Fisher Metric ⋮ Information Geometry and Quantum Fields

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Smooth structures on pseudomanifolds with isolated conical singularities
• Exponential statistical manifold
• Defining the curvature of a statistical problem (with applications to second order efficiency)
• Differential geometry of curved exponential families. Curvatures and information loss
• An information-geometric approach to a theory of pragmatic structuring
• A infinite-dimensional geometric structure on the space of all the probability measures equivalent to a given one
• The uniqueness of the Fisher metric as information metric
• Statistical manifolds are statistical models
• An Extended Cencov Characterization of the Information Metric
• A new mathematical framework for the study of linkage and selection
• The inverse function theorem of Nash and Moser
• Algebraic foundation of mathematical statistics²
• Connections on Non-Parametric Statistical Manifolds by Orlicz Space Geometry
• A geometric approach to complexity
• Information Geometry
• Statistical Isomorphism
• Equivalent Comparisons of Experiments
• An invariant form for the prior probability in estimation problems