Toric invariant theory for maximum likelihood estimation in log-linear models

DOI10.2140/ASTAT.2021.12.187MaRDI QIDQ2076293zbMATH OpenOpenAlexFDO

Authors Kathlén Kohn, Philipp Reichenbach, Anna Leah Seigal, Carlos Enrique Améndola Cerón

Publication date 16 February 2022

Published in Algebraic Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2012.07793

zbMATH Keywords

graphical modelslog-linear modelsmaximum likelihood estimationnull conescaling algorithmstorus actions

Mathematics Subject Classification ID

Geometric invariant theory (14L24) Applications of linear algebraic groups to the sciences (20G45) Point estimation (62F10) Probabilistic graphical models (62H22) Algebraic statistics (62R01)

Abstract: We establish connections between invariant theory and maximum likelihood estimation for discrete statistical models. We show that norm minimization over a torus orbit is equivalent to maximum likelihood estimation in log-linear models. We use notions of stability under a torus action to characterize the existence of the maximum likelihood estimate, and discuss connections to scaling algorithms.

Recommendations

• Invariant Theory and Scaling Algorithms for Maximum Likelihood Estimation
• The maximum likelihood degree of toric varieties
• The maximum likelihood degree
• Maximum Likelihood Estimation from a Tropical and a Bernstein–Sato Perspective
• Maximum likelihood estimation of toric Fano varieties

Cites work

• A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices
• Algebraic statistics
• An elementary proof of the Hilbert-Mumford criterion
• An Iterative Procedure for Estimation in Contingency Tables
• Biology
• Concerning nonnegative matrices and doubly stochastic matrices
• Convexity and Commuting Hamiltonians
• Generalized Iterative Scaling for Log-Linear Models
• Geometric Invariant Theory
• scientific article; zbMATH DE number 1134987 (Why is no real title available?)
• scientific article; zbMATH DE number 3195802 (Why is no real title available?)
• Invariant Theory and Scaling Algorithms for Maximum Likelihood Estimation
• Log-linear models for frequency tables derived by indirect observation: Maximum likelihood equations
• Maximum likelihood estimation in log-linear models
• On a Least Squares Adjustment of a Sampled Frequency Table When the Expected Marginal Totals are Known
• On the toric algebra of graphical models
• Orbits of linear algebraic groups
• Recent progress on scaling algorithms and applications

Cited in

(16)

• Moment maps, strict linear precision, and maximum likelihood degree one
• Discrete statistical models with rational maximum likelihood estimator
• Toric statistical models: parametric and binomial representations
• Maximum likelihood estimation of toric Fano varieties
• Invariant Theory and Scaling Algorithms for Maximum Likelihood Estimation
• Maximum likelihood estimation for tensor normal models via castling transforms
• Maximum Likelihood Estimation from a Tropical and a Bernstein–Sato Perspective
• Bayesian Integrals on Toric Varieties
• Toric geometry of entropic regularization
• Classical iterative proportional scaling of log-linear models with rational maximum likelihood estimator
• Corrigendum to: ``Invariant theory and scaling algorithms for maximum likelihood estimation
• Invariant theory in computational complexity and algebraic statistics
• A bridge between invariant theory and maximum likelihood estimation
• Complexity of robust orbit problems for torus actions and the abc-conjecture
• Maximum likelihood estimation of log-affine models using detailed-balanced reaction networks
• Classifying one-dimensional discrete models with maximum likelihood degree one

This page was built for publication: Toric invariant theory for maximum likelihood estimation in log-linear models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2076293)