On the toric algebra of graphical models
From MaRDI portal
Publication:2500459
DOI10.1214/009053606000000263zbMATH Open1104.60007arXivmath/0608054OpenAlexW2171712069MaRDI QIDQ2500459FDOQ2500459
Authors: Dan Geiger, Christopher Meek, Bernd Sturmfels 
Publication date: 24 August 2006
Published in: The Annals of Statistics (Search for Journal in Brave)
Abstract: We formulate necessary and sufficient conditions for an arbitrary discrete probability distribution to factor according to an undirected graphical model, or a log-linear model, or other more general exponential models. For decomposable graphical models these conditions are equivalent to a set of conditional independence statements similar to the Hammersley--Clifford theorem; however, we show that for nondecomposable graphical models they are not. We also show that nondecomposable models can have nonrational maximum likelihood estimates. These results are used to give several novel characterizations of decomposable graphical models.
Full work available at URL: https://arxiv.org/abs/math/0608054
Recommendations
Gröbner bases; other bases for ideals and modules (e.g., Janet and border bases) (13P10) Distribution theory (60E99)
Cites Work
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Logical and algorithmic properties of conditional independence and graphical models
- Algebraic algorithms for sampling from conditional distributions
- Title not available (Why is that?)
- Markov fields and log-linear interaction models for contingency tables
- Stratified exponential families: Graphical models and model selection
- Additive and multiplicative models and interactions
- Markov bases for decomposable graphical models
- Conditional Independences among Four Random Variables I
- Algebraic geometry of Bayesian networks
- Title not available (Why is that?)
- Geometry, moments and conditional independence trees with hidden variables.
- Gröbner bases and polyhedral geometry of reducible and cyclic models.
- Maximum Entropy for Hypothesis Formulation, Especially for Multidimensional Contingency Tables
- Markov Point Processes
- Title not available (Why is that?)
- Interactions in Multidimensional Contingency Tables
Cited In (77)
- Polynomial relations among principal minors of a \(4\times 4\)-matrix
- Total positivity in exponential families with application to binary variables
- Maximum likelihood estimation in the \(\beta\)-model
- Specializations of multigradings and the arithmetical rank of lattice ideals
- Positive margins and primary decomposition
- Tree cumulants and the geometry of binary tree models
- Equivalence classes of staged trees
- Markov bases of binary graph models of \(K_{4}\)-minor free graphs
- On the geometry of discrete exponential families with application to exponential random graph models
- Quasi-independence models with rational maximum likelihood estimator
- The maximum likelihood degree of toric varieties
- Algebraic structures in statistical methodology. Abstracts from the workshop held December 4--10, 2022
- Algebraic geometry of Bayesian networks
- A note on Gibbs and Markov random fields with constraints and their moments
- Markov bases of conditional independence models for permutations
- Mixture decompositions of exponential families using a decomposition of their sample spaces
- Higher Lawrence configurations.
- Natural gradient flow in the mixture geometry of a discrete exponential family
- One-dimensional Markov random fields, Markov chains and topological Markov fields
- Commutative algebra of statistical ranking
- Normal binary graph models
- Support sets in exponential families and oriented matroid theory
- MCMC using Markov bases for computing \(p\)-values in decomposable log-linear models
- Staged tree models with toric structure
- Indispensable binomials in semigroup ideals
- Minimal and minimal invariant Markov bases of decomposable models for contingency tables
- Symmetric measures via moments
- Graphical models for correlated defaults
- Equations defining probability tree models
- The space of compatible full conditionals is a unimodular toric variety
- Three Counter-Examples on Semi-Graphoids
- On the role of the overall effect in exponential families
- A Markov basis for conditional test of common diagonal effect in quasi-independence model for square contingency tables
- Markov bases for two-way subtable sum problems
- A class of statistical models to weaken independence in two-way contingency tables
- Minimal primes of ideals arising from conditional independence statements
- Epistemic conditions for rationalizability
- Computing images of polynomial maps
- Discovery of statistical equivalence classes using computer algebra
- The algebra of reversible Markov chains
- Gröbner bases and polyhedral geometry of reducible and cyclic models.
- On the closure of relational models
- Decompositions of binomial ideals
- Optimally approximating exponential families
- A Gröbner basis characterization for chordal comparability graphs
- Generalisation of the Hammersley-Clifford theorem on bipartite graphs
- Bayes factors and the geometry of discrete hierarchical loglinear models
- Maximum likelihood estimation in log-linear models
- Toric invariant theory for maximum likelihood estimation in log-linear models
- Markov random fields, Markov cocycles and the 3-colored chessboard
- A note on faithfulness and total positivity
- Conditions for swappability of records in a microdata set when some marginals are fixed
- Toric statistical models: parametric and binomial representations
- Moment maps, strict linear precision, and maximum likelihood degree one
- A variational principle for ground spaces
- Conjunctive Bayesian networks
- Cumulant varieties
- Ideals of graph homomorphisms
- A short history of algebraic statistics
- Maximizing the Divergence from a Hierarchical Model of Quantum States
- Decomposable context-specific models
- Sampling lattice points in a polytope: a Bayesian biased algorithm with random updates
- Markov Bases: A 25 Year Update
- Classical iterative proportional scaling of log-linear models with rational maximum likelihood estimator
- On factorization of probability distributions over directed graphs.
- Maximizing the Bregman divergence from a Bregman family
- Symmetrically Colored Gaussian Graphical Models with Toric Vanishing Ideals
- Variations on undirected graphical models and their relationships
- When Does a Mixture of Products Contain a Product of Mixtures?
- The face lattice of the set of reduced density matrices and its coatoms
- Compression schemes for concept classes induced by three types of discrete undirected graphical models
- Nonlinear algebra and applications
- Dimension of Marginals of Kronecker Product Models
- A new characterization of discrete decomposable graphical models
- Game theory of undirected graphical models
- Testing the fit of relational models
- Toric and Non-toric Bayesian Networks
Uses Software
This page was built for publication: On the toric algebra of graphical models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2500459)
