Algebra, Geometry and Computer Algebra Group

Bernd Sturmfels, MPI Leipzig: Discrete Statistical Models with Rational Maximum Likelihood Estimator


Referent: Bernd Sturmfels, Discrete Statistical Models with Rational Maximum Likelihood Estimator

Donnerstag,  17.10.2019, 16:00 h

Ort:Raum 418-210

 

A discrete statistical model is a subset of a probability simplex.
Its maximum likelihood estimator (MLE) is a retraction from that simplex
onto the model. We characterize all models for which this retraction is a
rational function. This is a contribution via real algebraic geometry
which rests on results due to Huh and Kapranov on Horn uniformization.
Our discussion centers around models that are used in practise, like
Bayesian networks, decomposable graphical models, and staged trees.
This is joint work with Eliana Duarte and Orlando Marigliano.
Go to top