Complete Collineations for Maximum Likelihood Estimation
SIAM Journal on Applied Algebra and Geometry · 30.06.2026 · 10 (2) · 261-302
DOI: 10.1137/24m1694793 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Applied Algebra and Geometry, online erschienen am 10.06.2026. Verfasst von Gergely Bérczi und 3 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Gefördert von: Aarhus Universitet, European Research Council, National Science Foundation.
Abstract (Originalsprache)
We import the algebro-geometric notion of a complete collineation into the study of maximum likelihood estimation in directed Gaussian graphical models. A complete collineation produces a perturbation of sample data, which we call a stabilization of the sample. While a maximum likelihood estimate (MLE) may not exist or be unique given sample data, it is always unique given a stabilization. We relate the MLE given a stabilization to the MLE given original sample data, when one exists, providing necessary and sufficient conditions for the MLE given a stabilization to be one given the original sample. We show that the MLE has a well-defined limit as the stabilization of a sample tends to the original sample, and that the limit is an MLE given the original sample, when one exists. Finally, we address the question of which MLEs given a sample can arise as such limits.
Förderung
- Aarhus Universitet
- European Research Council
- National Science Foundation
Zitieren
APA
Bérczi, G., Hamilton, E., Reichenbach, P., & Seigal, A. (2026). Complete Collineations for Maximum Likelihood Estimation. SIAM Journal on Applied Algebra and Geometry, 10(2), 261-302. https://doi.org/10.1137/24m1694793
Vancouver
Bérczi G, Hamilton E, Reichenbach P, Seigal A. Complete Collineations for Maximum Likelihood Estimation. SIAM Journal on Applied Algebra and Geometry. 2026;10(2):261-302. doi:10.1137/24m1694793
BibTeX
@article{Brczi2026,
author = {Bérczi, Gergely and Hamilton, Eloise and Reichenbach, Philipp and Seigal, Anna},
title = {Complete Collineations for Maximum Likelihood Estimation},
journal = {SIAM Journal on Applied Algebra and Geometry},
year = {2026},
volume = {10},
number = {2},
pages = {261--302},
doi = {10.1137/24m1694793}
}
EUVIMED