Classifying one-dimensional discrete models with maximum likelihood degree one

by   Arthur Bik, et al.

We propose a classification of all one-dimensional discrete statistical models with maximum likelihood degree one based on their rational parametrization. We show how all such models can be constructed from members of a smaller class of 'fundamental models' using a finite number of simple operations. We introduce 'chipsplitting games', a class of combinatorial games on a grid which we use to represent fundamental models. This combinatorial perspective enables us to show that there are only finitely many fundamental models in the probability simplex Δ_n for n≤ 4.


page 1

page 2

page 3

page 4


Discrete Statistical Models with Rational Maximum Likelihood Estimator

A discrete statistical model is a subset of a probability simplex. Its m...

Maximum Likelihood Joint Tracking and Association in a Strong Clutter without Combinatorial Complexity

We have developed an efficient algorithm for the maximum likelihood join...

The maximum likelihood degree of sparse polynomial systems

We consider statistical models arising from the common set of solutions ...

Quasi-independence models with rational maximum likelihood estimates

We classify the two-way independence quasi-independence models (or indep...

Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions

Integrating discrete probability distributions and combinatorial optimiz...

Families of polytopes with rational linear precision in higher dimensions

In this article we introduce a new family of lattice polytopes with rati...

Inverse-Weighted Survival Games

Deep models trained through maximum likelihood have achieved state-of-th...