Skip to main content

Adaptive grid sampling for hierarchical Bayesian models

Primary supervisor

Daniel Schmidt

Learning appropriate prior distributions from replications of experiments is a important problem in the space of hierarchical and empirical Bayes. In this problem, we exploit the fact that we have multiple repeats of similar experiments and pool these to learn an appropriate prior distribution for the unknown parameters of this set of problems. Standard solutions to this type of problem tend to be of mixed Bayesian and non-Bayesian form, and are somewhat ad-hoc in nature.

Student cohort

Double Semester

Aim/outline

This project aims to examine the use of grid sampling within the context of hierarchical Bayesian modelling to provide an adaptive, simple and fully Bayesian solution to the problem. Specifically, it would examine grid samplers with a concept of enforced smoothness as a basis for adaptive prior distributions that can be learned from an ensemble of data.

Required knowledge

Python and/or R; some knowledge of Bayesian statistics.