This work presents a new model that extends the hubs weighted graphical lasso to dynamic settings by combining it with a Hidden Markov framework. The method is designed to track changes in the network structure over time, especially when hub nodes are present. A penalized EM algorithm is used for estimation, and simulations suggest notable improvements over other HMM-based approaches. Future work will explore how the model behaves when the number of states is overestimated.
Evaluating hub structures in hidden Markov graphical models / Foroni, Beatrice; Khalili, Abbas; Petrella, Lea; Salvati, Nicola. - (2025), pp. 421-427. (Intervento presentato al convegno SIS: Scientific Meeting of the Italian Statistical Society tenutosi a Genova) [10.1007/978-3-031-96736-8].
Evaluating hub structures in hidden Markov graphical models
Beatrice Foroni
Primo
;Lea PetrellaPenultimo
;
2025
Abstract
This work presents a new model that extends the hubs weighted graphical lasso to dynamic settings by combining it with a Hidden Markov framework. The method is designed to track changes in the network structure over time, especially when hub nodes are present. A penalized EM algorithm is used for estimation, and simulations suggest notable improvements over other HMM-based approaches. Future work will explore how the model behaves when the number of states is overestimated.| File | Dimensione | Formato | |
|---|---|---|---|
|
Foroni_Evaluating-Hub-Structures_2025.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.01 MB
Formato
Adobe PDF
|
1.01 MB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
