Dear Colleagues,

as part of the Visiting Professors program of the Master's Degree in Stochastics and Data Science at the University of Torino (full program available at https://www.master-sds.unito.it/go/visiting), we are pleased to announce the following short course:

———————————————————

Kolyan RAY (Imperial College London)

POSTERIOR ASYMPTOTICS IN BAYESIAN NONPARAMETRICS

This mini-course will cover an introduction into the asymptotic theory for Bayesian nonparametric procedures. This provides a useful tool to understand how prior choices can affect the statistical performance of the Bayes method in high or infinite dimensional models. We will cover the notion of posterior consistency and convergence rates, using Gaussian process priors as a canonical example. At the end, we will also touch on recent extensions of such theory to variational Bayes, which provides a scalable posterior approximation algorithm.

———————————————————

The course will be held exclusively in-person, according to the following schedule:

- Tue Dec 10, h. 9.15-11.15 - Wed Dec 11, h. 11.15-13.00 - Thu Dec 12, h. 9.15-11.15 - Thu Dec 12, h. 14.00-16.00

Course location: Room 30, third floor, Corso Unione Sovietica 218/bis, 10134, Torino.

The participation is open to everyone interested.

Best regards, Matteo Ruggiero

--- Matteo Ruggiero University of Torino and Collegio Carlo Alberto www.matteoruggiero.it