Σεμινάριο: "Decreasing weights priors and their applications"

ΚΥΚΛΟΣ ΣΕΜΙΝΑΡΙΩΝ ΣΤΑΤΙΣΤΙΚΗΣ 2024-2025

Ομιλητής: Christos Merkatas, Department of Statistics and Actuarial-Financial Mathematics, University of the Aegean

ΑΙΘΟΥΣΑ Τ105, Κτίριο Τροίας

ΠΕΡΙΛΗΨΗ

Decreasing weight prior distributions for mixture models play an important role in nonparametric Bayesian inference. Various random probability measures with decreasing weights have been previously explored and it has been shown that they provide an efficient alternative to the more traditional Dirichlet process mixture model. In this talk, a general procedure to define any decreasing weights model based on a characterization of a discrete random variable will be given, and their applications in density estimation and system identification problems will be presented.