TU Berlin

Fachgebiet Algorithmische AlgebraPublications

Inhalt des Dokuments

zur Navigation

Search for Publication

Suche nach Publikationen




All Publications

Invariant Theory and Scaling Algorithms for Maximum Likelihood Estimation
Zitatschlüssel AKRS-InvariantTheoryAndScalingAlgorithmsForMaximumLikelihoodEstimation
Autor Carlos Améndola and Kathlén Kohn and Philipp Reichenbach and Anna Seigal
Jahr 2020
Zusammenfassung We show that maximum likelihood estimation in statistics is equivalent to finding the capacity in invariant theory, in two statistical settings: log-linear models and Gaussian transformation families.The former includes the classical independence model while the latter includes matrix normal models and Gaussian graphical models given by transitive directed acyclic graphs. We use stability under group actions to characterize boundedness of the likelihood, and existence and uniqueness of the maximum likelihood estimate. Our approach reveals promising consequences of the interplay between invariant theory and statistics. In particular, existing scaling algorithms from statistics can be used in invariant theory, and vice versa.
Link zur Publikation Download Bibtex Eintrag

Navigation

Direktzugang

Schnellnavigation zur Seite über Nummerneingabe