Mitchell Centre Seminar Series: Alberto Caimo
| Dates: | 12 November 2014 |
|---|
| Times: | 16:00 - 17:30 |
|---|
| What is it: | Seminar |
|---|
| Organiser: | School of Social Sciences |
|---|
| Who is it for: | University staff, Current University students |
|---|
| Speaker: | Alberto Caimo |
|---|
|
HBS G6
Alberto Caimo
Efficient Bayesian computation for exponential random graph models
Powerful ideas recently appeared in the literature are adjusted and combined to design improved samplers for doubly intractable target distributions with a focus on Bayesian exponential random graph models. Different forms of adaptive Metropolis-Hastings proposals (vertical, horizontal and rectangular) are tested and merged with the delayed rejection (DR) strategy with the aim of reducing the variance of the resulting MCMC estimators for a given computational time. The DR is modified in order to integrate it within the approximate exchange algorithm (AEA) to avoid the computation of intractable normalising constant that appears in exponential random graph models. This gives rise to the AEA+DR: a new methodology to sample doubly intractable distributions that dominates the AEA in the Peskun ordering leading to MCMC estimators with a smaller asymptotic variance.
Speaker
Alberto Caimo
Role: Postdoc
Organisation: University of Lugano
Travel and Contact Information
Find event
G6
Humanities Bridgeford Street
Manchester
