Toric invariant theory for maximum likelihood estimation in log-linear models
Algebraic Statistics · 2021
DOI: 10.2140/astat.2021.12.187 ↗Kurz gefasst
Fachartikel in der Zeitschrift Algebraic Statistics, 2021. Verfasst von Carlos Améndola und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 25 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Améndola, C., Kohn, K., Reichenbach, P., & Seigal, A. (2021). Toric invariant theory for maximum likelihood estimation in log-linear models. Algebraic Statistics. https://doi.org/10.2140/astat.2021.12.187
Vancouver
Améndola C, Kohn K, Reichenbach P, Seigal A. Toric invariant theory for maximum likelihood estimation in log-linear models. Algebraic Statistics. 2021. doi:10.2140/astat.2021.12.187
BibTeX
@article{Amndola2021,
author = {Améndola, Carlos and Kohn, Kathlén and Reichenbach, Philipp and Seigal, Anna},
title = {Toric invariant theory for maximum likelihood estimation in log-linear models},
journal = {Algebraic Statistics},
year = {2021},
doi = {10.2140/astat.2021.12.187}
}
EUVIMED