Bayes as Optimization

Probability Seminar

Daniel Sanz-Alonso (Brown University)

Thursday, March 8, 2018 -
3:15pm to 4:15pm
Location: 
119 Physics

In this talk I will revisit the idea of viewing the Bayesian update as a variational problem. I will show how the variational interpretation is helpful in establishing the convergence of Bayesian models, and in defining and analysing diffusion processes that have the posterior as invariant measure. I will illustrate the former by proving a consistency result for graph-based Bayesian semi-supervised learning in the large unlabelled data-set regime, and the latter by suggesting new optimality criteria for the choice of metric in Riemannian MCMC.

Last updated: 2018/05/21 - 12:02am