Welcome to the webpage of the BNP & Stochastic Processes initiative. Seeded by a CONTEX
project (2018-9B), the purpose of this forum is to promote and foster research activities around the intersection
of two rich areas of mathematical research, Bayesian Nonparametrics and Stochastic Processes.
From its origins Bayesian Nonparametric methods have relied on the theory of Stochastic Processes to create
nonparametric priors for statistical analysis. On its counterpart, the theory and frontier applications of Bayesian
Nonparametrics has served as a gateway to create new and general stochastic models, reshaping the inference paradigm. The
intersection of these two areas results in a fascinating world full of novel and realistic models, able to capture the
data complexity of modern data science.
1 Ayala, D., Jofré, L., Gutiérrez, L. and Mena, R.H. (2020). On a Bayesian nonparametric mixture representation of phase-type distributions. Submitted manuscript.
2 Chae, M. and Walker, S.G. (2020). Wasserstein upper bounds of the total variation for smooth densities. Statistics and Probability Letters. 163: 108771.
6 Mena, R.H., Velasco-Hernandez, J.X, Mantilla-Beniers, N.B., Carranco-Sapiéns, G.A., Benet, L.,
Boyer, D. and
Pérez-Castillo, I. (2020). Using the posterior predictive distribution to analyse epidemic models: COVID-19 in
Mexico
City. Physical Biology, In press. https://doi.org/10.1088/1478-3975/abb115