Dimension of Marginals of Kronecker Product Models
From MaRDI portal
Publication:5347296
Abstract: A Kronecker product model is the set of visible marginal probability distributions of an exponential family whose sufficient statistics matrix factorizes as a Kronecker product of two matrices, one for the visible variables and one for the hidden variables. We estimate the dimension of these models by the maximum rank of the Jacobian in the limit of large parameters. The limit is described by the tropical morphism; a piecewise linear map with pieces corresponding to slicings of the visible matrix by the normal fan of the hidden matrix. We obtain combinatorial conditions under which the model has the expected dimension, equal to the minimum of the number of natural parameters and the dimension of the ambient probability simplex. Additionally, we prove that the binary restricted Boltzmann machine always has the expected dimension.
Recommendations
- scientific article; zbMATH DE number 1536319
- Models with a Kronecker product covariance structure: estimation and testing
- On Estimation of Covariance Matrices With Kronecker Product Structure
- Dimension Estimation and Models
- scientific article; zbMATH DE number 5263528
- scientific article
- On the dimension of product measures
- Marginal-frechet-bounds for multidimensional distribution functions
- Existence and uniqueness of the maximum likelihood estimator for models with a Kronecker product covariance structure
Cites work
- scientific article; zbMATH DE number 3834108 (Why is no real title available?)
- scientific article; zbMATH DE number 5968745 (Why is no real title available?)
- scientific article; zbMATH DE number 436950 (Why is no real title available?)
- scientific article; zbMATH DE number 3133919 (Why is no real title available?)
- scientific article; zbMATH DE number 5777868 (Why is no real title available?)
- scientific article; zbMATH DE number 44577 (Why is no real title available?)
- scientific article; zbMATH DE number 1024657 (Why is no real title available?)
- scientific article; zbMATH DE number 773851 (Why is no real title available?)
- scientific article; zbMATH DE number 3282328 (Why is no real title available?)
- A brief proof of a maximal rank theorem for generic double points in projective space
- A tropical approach to secant dimensions
- An implicitization challenge for binary factor analysis
- Decompositions of a Higher-Order Tensor in Block Terms—Part I: Lemmas for Partitioned Matrices
- Discrete restricted Boltzmann machines
- Graphical models, exponential families, and variational inference
- Hierarchical Models, Marginal Polytopes, and Linear Codes
- Hierarchical models as marginals of hierarchical models
- Induction for secant varieties of Segre varieties
- Information Theory and Statistical Mechanics
- Learning deep architectures for AI
- Lectures on algebraic statistics
- Mixture decompositions of exponential families using a decomposition of their sample spaces
- Neighborliness of marginal polytopes
- On direct product matrices
- On the Alexander-Hirschowitz theorem
- On the dimensions of secant varieties of Segre-Veronese varieties
- On the toric algebra of graphical models
- Ranks of tensors, secant varieties of Segre varieties and fat points
- Refinements of universal approximation results for deep belief networks and restricted Boltzmann machines
- Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
- Secant varieties of Segre-Veronese varieties
- Secant varieties of \({\mathbb {P}^1}\times \cdots \times {\mathbb {P}^1} (n\)-times) are not defective for \(n \geq 5\)
- Stochastic complexity and generalization error of a restricted Boltzmann machine in Bayesian estimation
- Support sets in exponential families and oriented matroid theory
- When does a mixture of products contain a product of mixtures?
This page was built for publication: Dimension of Marginals of Kronecker Product Models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5347296)
