Mixture decompositions of exponential families using a decomposition of their sample spaces

zbMath1266.60038arXiv1008.0204MaRDI QIDQ4917828

Guido Montúfar

Publication date: 2 May 2013

Full work available at URL: https://arxiv.org/abs/1008.0204

zbMATH Keywords

mixture modelperfect codemarginal polytopenon-negative tensor rank

Mathematics Subject Classification ID

Approximations to statistical distributions (nonasymptotic) (62E17) Distribution theory (60E99)

Related Items

Hierarchical models as marginals of hierarchical models, Dimension of Marginals of Kronecker Product Models, Universal Approximation Depth and Errors of Narrow Belief Networks with Discrete Units, When Does a Mixture of Products Contain a Product of Mixtures?

Uses Software

• polymake
• PRMLT

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
• Support sets in exponential families and oriented matroid theory
• Prodsimplicial-neighborly polytopes
• Erratum to: Neighborliness of marginal polytopes
• The geometry of exponential families
• Uses of exchangeability
• Finite forms of de Finetti's theorem on exchangeability
• PRMLT
• Gröbner bases and polyhedral geometry of reducible and cyclic models.
• On the toric algebra of graphical models
• Refinements of Universal Approximation Results for Deep Belief Networks and Restricted Boltzmann Machines
• Secant varieties of ℙ¹×⋯×ℙ¹ (𝕟-times) are NOT defective for 𝕟≥5
• Hierarchical Models, Marginal Polytopes, and Linear Codes
• Singular value decomposition of probability matrices: Probabilistic aspects of latent dichotomous variables
• Information geometry on hierarchy of probability distributions
• On the identifiability of binary Segre products
• Finding the Maximizers of the Information Divergence From an Exponential Family