The Maximum Likelihood Degree of Toric Models is Monotonic

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Améndola, Carlos, Oldekop, Janike, Wiesmann, Maximilian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909674947739648
author Améndola, Carlos
Oldekop, Janike
Wiesmann, Maximilian
author_facet Améndola, Carlos
Oldekop, Janike
Wiesmann, Maximilian
contents We settle a conjecture by Coons and Sullivant stating that the maximum likelihood (ML) degree of a facial submodel of a toric model is at most the ML degree of the model itself. We discuss the impact on the ML degree from observing zeros in the data. Moreover, we connect this problem to tropical likelihood degenerations, and show how the results can be applied to discrete graphical and quasi-independence models.
format Preprint
id arxiv_https___arxiv_org_abs_2507_02719
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Maximum Likelihood Degree of Toric Models is Monotonic
Améndola, Carlos
Oldekop, Janike
Wiesmann, Maximilian
Algebraic Geometry
Statistics Theory
62R01, 14M25, 13P15, 62F10, 14T90
We settle a conjecture by Coons and Sullivant stating that the maximum likelihood (ML) degree of a facial submodel of a toric model is at most the ML degree of the model itself. We discuss the impact on the ML degree from observing zeros in the data. Moreover, we connect this problem to tropical likelihood degenerations, and show how the results can be applied to discrete graphical and quasi-independence models.
title The Maximum Likelihood Degree of Toric Models is Monotonic
topic Algebraic Geometry
Statistics Theory
62R01, 14M25, 13P15, 62F10, 14T90
url https://arxiv.org/abs/2507.02719