Mario Beraha and Alessandra Guglielmi
Published in Bayesian Analysis, 2019
In this work, we comment on the article by Camerlenghi and co authors, proposing an approximation to their latent nested process, that we obtain by truncating a priori the stick-breaking construction of a nested Dirichlet Process.
Giulia Bissoli, Celeste Principi, Gian Matteo Rinaldi, Mario Beraha and Alessandra Guglielmi
Published in Book of Short Papers Sis 2019, 2019
In this work, we propose a Bayesian model for the analysis of flow counts on a network for an application to a bike sharing platform (BikeMi) in Milano.
Mario Beraha, Alberto Maria Metelli, Matteo Papini, Andrea Tirinzoni and Marcello Restelli
Published in International Joint Conference on Neural Networks, 2019
In this paper, we tackle the problem of feature selection for both classification and regression problems. We find a new bound for the classification and regression error achieved by the ideal classifier working on different subsets of features.