Multivariate Gaussians, semidefinite matrix completion, and convex algebraic geometry
From MaRDI portal
Publication:2634801
convex algebraic geometrydual convex conedual projective varietymaximum likelihood estimationmultivariate normal distributionsemidefinite matrix completion
Graphs and linear algebra (matrices, eigenvalues, etc.) (05C50) Gröbner bases; other bases for ideals and modules (e.g., Janet and border bases) (13P10) Positive matrices and their generalizations; cones of matrices (15B48) Estimation in multivariate analysis (62H12) Multivariate analysis (62H99) Algebraic statistics (62R01)
Abstract: We study multivariate normal models that are described by linear constraints on the inverse of the covariance matrix. Maximum likelihood estimation for such models leads to the problem of maximizing the determinant function over a spectrahedron, and to the problem of characterizing the image of the positive definite cone under an arbitrary linear projection. These problems at the interface of statistics and optimization are here examined from the perspective of convex algebraic geometry.
Recommendations
- The maximum likelihood degree of linear spaces of symmetric matrices
- Maximum likelihood degree of the two-dimensional linear Gaussian covariance model
- Maximum likelihood for matrices with rank constraints
- Maximum likelihood estimation for linear Gaussian covariance models
- The maximum likelihood degree
Cites work
- A broken circuit ring
- A Combinatorial Model for Series-Parallel Networks
- Algebraic geometry of Bayesian networks
- Algebraic geometry of Gaussian Bayesian networks
- Algebraic Statistics for Computational Biology
- Algebras generated by reciprocals of linear forms
- Covariance hypothesis which are linear in both the covariance and the inverse covariance
- Determinant Maximization with Linear Matrix Inequality Constraints
- Determinantal ideals of linear type of a generic symmetric matrix
- Facing up to arrangements: face-count formulas for partitions of space by hyperplanes
- Hilbert series of residual intersections
- scientific article; zbMATH DE number 3673370 (Why is no real title available?)
- scientific article; zbMATH DE number 44577 (Why is no real title available?)
- scientific article; zbMATH DE number 49099 (Why is no real title available?)
- scientific article; zbMATH DE number 469396 (Why is no real title available?)
- scientific article; zbMATH DE number 3418508 (Why is no real title available?)
- Ideals with sliding depth
- Lectures on algebraic statistics
- On quasi-complete intersections
- On the sparsity order of a graph and its deficiency in chordality
- Polyhedral conditions for the nonexistence of the MLE for hierarchical log-linear models
- Positive definite completions of partial Hermitian matrices
- Positive semidefinite matrices with a given sparsity pattern
- SINGULAR
- The algebraic degree of semidefinite programming
- The real positive definite completion problem for a simple cycle
- The real positive definite completion problem: cycle completability
- Trek separation for Gaussian graphical models
Cited in
(60)- Discriminant analysis with Gaussian graphical tree models
- Gaussian graphical models with toric vanishing ideals
- Bad projections of the PSD cone
- The leading coefficient of Lascoux polynomials
- Directed Gaussian graphical models with toric vanishing ideals
- Lefschetz properties in algebra, geometry and combinatorics. Abstracts from the workshop held September 27 -- October 3, 2020 (hybrid meeting)
- A review of Gaussian Markov models for conditional independence
- Real rank geometry of ternary forms
- Estimating linear covariance models with numerical nonlinear algebra
- Exponential varieties
- Algebraic boundaries of convex semi-algebraic sets
- On a parametrization of positive semidefinite matrices with zeros
- ORBITOPES
- Extremal positive semidefinite matrices whose sparsity pattern is given by graphs without \(K_{5}\) minors
- Geometry of maximum likelihood estimation in Gaussian graphical models
- Pencils of quadrics: old and new
- Equations and multidegrees for inverse symmetric matrix pairs
- Reciprocal maximum likelihood degrees of Brownian motion tree models
- Reciprocal maximum likelihood degrees of diagonal linear concentration models
- scientific article; zbMATH DE number 7476198 (Why is no real title available?)
- The degree of the central curve in semidefinite, linear, and quadratic programming
- Coloured graphical models and their symmetries
- Inverting catalecticants of ternary quartics
- The maximum likelihood degree of linear spaces of symmetric matrices
- Likelihood geometry of correlation models
- Generic Spectrahedral Shadows
- Maximum likelihood estimation for linear Gaussian covariance models
- The notion of a rational convex program, and an algorithm for the Arrow-Debreu Nash bargaining game
- Maximum likelihood degree, complete quadrics, and \(\mathbb{C}^*\)-action
- Symmetrically Colored Gaussian Graphical Models with Toric Vanishing Ideals
- Real algebraic geometry with a view toward Koopman operator methods. Abstracts from the workshop held March 12--17, 2023
- Gaussian Likelihood Geometry of Projective Varieties
- Nonlinear algebra and applications
- Symmetries in directed Gaussian graphical models
- Logarithmic Voronoi cells for Gaussian models
- Multidegrees, prime ideals, and non-standard gradings
- Ideals of submaximal minors of sparse symmetric matrices
- Discriminants and nonnegative polynomials
- The tropical critical points of an affine matroid
- Complete quadrics: Schubert calculus for Gaussian models and semidefinite programming
- Differential equations for Gaussian statistical models with rational maximum likelihood estimator
- Invariant theory in computational complexity and algebraic statistics
- Initial values of ML-degree polynomials
- Gibbs manifolds
- Proof of a conjecture of Sturmfels, Timme and Zwiernik
- Applications of intersection theory and gradients: from maximum likelihood to chromatic polynomials
- Entropic covariance models
- Conditional Euclidean distance optimization via relative tangency
- Classifying one-dimensional discrete models with maximum likelihood degree one
- Optimal designs for discrete choice models via graph Laplacians
- The central curve in linear programming
- Applications of singularity theory in applied algebraic geometry and algebraic statistics
- The F-adjoined Gauss map and Gaussian likelihood geometry
- Homaloidal polynomials and Gaussian models of maximum likelihood degree 1
- Logarithmically sparse symmetric matrices
- Lissajous varieties
- Sullivant-Talaska ideal of the cyclic Gaussian graphical model
- Complete collineations for maximum likelihood estimation
- Characteristic numbers and chromatic polynomial of a tensor
- Binomiality of undirected colored Gaussian graphical models
This page was built for publication: Multivariate Gaussians, semidefinite matrix completion, and convex algebraic geometry
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2634801)