[ENGLISH BELOW] Con preghiera di diffusione,

si avvisa che in data 05-11-2024, alle ore 11:00 precise, presso la sala Pentagonale dell'Area della Ricerca 1 del CNR di Milano in via A. Corti 12,

la Dr. Alice Giampino, Università degli Studi di Milano-Bicocca, terrà un seminario dal titolo

A Bayesian Model for Co-clustering Ordinal Data with Informative Missing Entries

Abstract: Several approaches have been proposed in the literature for clustering multivariate ordinal data. These methods typically treat missing values as absent information, rather than recognizing them as valuable for profiling population characteristics. To address this gap, we introduce a Bayesian nonparametric model for co-clustering multivariate ordinal data that treats censored observations as informative, rather than merely missing. We demonstrate that this offers a significant improvement in understanding the underlying structure of the data. Our model exploits the flexibility of two independent Dirichlet processes, allowing us to infer potentially distinct subpopulations that characterize the latent structure of both subjects and variables. The ordinal nature of the data is addressed by introducing latent variables, while a matrix factorization specification is adopted to handle the high dimensionality of the data in a parsimonious way. The conjugate structure of the model enables an explicit derivation of the full conditional distributions of all the random variables in the model, which facilitates seamless posterior inference using a Gibbs sampling algorithm. We demonstrate the method's performance through simulations and by analyzing politician and movie ratings data.

Gli interessati potranno partecipare al seminario da remoto, utilizzando il link indicato qui sotto https://teams.microsoft.com/l/meetup-join/19%3ameeting_OTk1YjcxOWMtYjQzYy00M... oppure in presenza previa prenotazione via email a federico.cortese@mi.imati.cnr.itmailto:federico.cortese@mi.imati.cnr.it

Distinti saluti, Federico P. Cortese

***ENGLISH*** Dear all,

We are honoured to announce that on 11/05/2024, at 11:00 AM, in the Pentagonale Room of the CNR Research Area 1 in Milan, Via A. Corti 12,

Dr. Alice Giampino from the University of Milano-Bicocca will present a seminar titled:

A Bayesian Model for Co-clustering Ordinal Data with Informative Missing Entries

Abstract: Several approaches have been proposed in the literature for clustering multivariate ordinal data. These methods typically treat missing values as absent information, rather than recognizing them as valuable for profiling population characteristics. To address this gap, we introduce a Bayesian nonparametric model for co-clustering multivariate ordinal data that treats censored observations as informative, rather than merely missing. We demonstrate that this offers a significant improvement in understanding the underlying structure of the data. Our model exploits the flexibility of two independent Dirichlet processes, allowing us to infer potentially distinct subpopulations that characterize the latent structure of both subjects and variables. The ordinal nature of the data is addressed by introducing latent variables, while a matrix factorization specification is adopted to handle the high dimensionality of the data in a parsimonious way. The conjugate structure of the model enables an explicit derivation of the full conditional distributions of all the random variables in the model, which facilitates seamless posterior inference using a Gibbs sampling algorithm. We demonstrate the method's performance through simulations and by analyzing politician and movie ratings data.

Interested participants may attend the seminar remotely using the link provided below: https://teams.microsoft.com/l/meetup-join/19%3ameeting_OTk1YjcxOWMtYjQzYy00M...

or in person by reserving a spot via email at federico.cortese@mi.imati.cnr.itmailto:federico.cortese@mi.imati.cnr.it

Best regards, Federico P. Cortese

To unsubscribe from this group and stop receiving emails from it, send an email to all_ricercatori+unsubscribe@imati.cnr.itmailto:all_ricercatori+unsubscribe@imati.cnr.it.