RT info:eu-repo/semantics/article
T1 Eigenvalues and constraints in mixture modeling: geometric and computational issues
A1 García Escudero, Luis Ángel
A1 Gordaliza Ramos, Alfonso
A1 Greselin, Francesca
A1 Salvatore, Ingrassia
A1 Mayo Iscar, Agustín
AB This paper presents a review about the usage of eigenvalues restrictionsfor constrained parameter estimation in mixtures of elliptical distributionsaccording to the likelihood approach. These restrictions serve a twofoldpurpose: to avoid convergence to degenerate solutions and to reduce the onsetof non interesting (spurious) maximizers, related to complex likelihood surfaces.The paper shows how the constraints may play a key role in the theoryof Euclidean data clustering. The aim here is to provide a reasoned reviewof the constraints and their applications, along the contributions of many authors,spanning the literature of the last thirty years.
YR 2018
FD 2018
LK http://uvadoc.uva.es/handle/10324/32021
UL http://uvadoc.uva.es/handle/10324/32021
LA spa
NO Advances in Data Analysis and Classification, 2018, vol. 12. p. 203-233
DS UVaDOC
RD 22-nov-2024