Mixture decompositions of exponential families using a decomposition of their sample spaces
From MaRDI portal
Publication:4917828
Abstract: We study the problem of finding the smallest such that every element of an exponential family can be written as a mixture of elements of another exponential family. We propose an approach based on coverings and packings of the face lattice of the corresponding convex support polytopes and results from coding theory. We show that is the smallest number for which any distribution of -ary variables can be written as mixture of independent -ary variables. Furthermore, we show that any distribution of binary variables is a mixture of elements of the -interaction exponential family.
Recommendations
Cites work
- scientific article; zbMATH DE number 3133919 (Why is no real title available?)
- scientific article; zbMATH DE number 44577 (Why is no real title available?)
- scientific article; zbMATH DE number 665689 (Why is no real title available?)
- scientific article; zbMATH DE number 1024657 (Why is no real title available?)
- scientific article; zbMATH DE number 1182906 (Why is no real title available?)
- scientific article; zbMATH DE number 1560711 (Why is no real title available?)
- scientific article; zbMATH DE number 3223483 (Why is no real title available?)
- scientific article; zbMATH DE number 3261280 (Why is no real title available?)
- Erratum to: Neighborliness of marginal polytopes
- Finding the Maximizers of the Information Divergence From an Exponential Family
- Finite forms of de Finetti's theorem on exchangeability
- Finite mixture models
- Gröbner bases and polyhedral geometry of reducible and cyclic models.
- Hierarchical Models, Marginal Polytopes, and Linear Codes
- Information geometry on hierarchy of probability distributions
- Maximizing multi-information
- Mixture models: theory, geometry and applications
- On the identifiability of binary Segre products
- On the toric algebra of graphical models
- PRMLT
- Pattern recognition and machine learning.
- Prodsimplicial-neighborly polytopes
- Refinements of universal approximation results for deep belief networks and restricted Boltzmann machines
- Secant varieties of \({\mathbb {P}^1}\times \cdots \times {\mathbb {P}^1} (n\)-times) are not defective for \(n \geq 5\)
- Singular value decomposition of probability matrices: Probabilistic aspects of latent dichotomous variables
- Statistical analysis of finite mixture distributions
- Support sets in exponential families and oriented matroid theory
- The geometry of exponential families
- Uses of exchangeability
- polymake: a framework for analyzing convex polytopes
Cited in
(6)- Information geometry on hierarchy of probability distributions
- When does a mixture of products contain a product of mixtures?
- Universal Approximation Depth and Errors of Narrow Belief Networks with Discrete Units
- Dimension of Marginals of Kronecker Product Models
- An exact decomposition theorem and a unified view of some related distributions for a class of exponential transformation models on symmetric cones
- Hierarchical models as marginals of hierarchical models
This page was built for publication: Mixture decompositions of exponential families using a decomposition of their sample spaces
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4917828)