Thursday 28 Mar 2019: Simple likelihood approximations for latent variable models: computational and statistical scalability
Dr Anthony Lee - University of Bristol
Laver LT6 14:30-15:30
A popular statistical modelling technique is to model data as a partial observation of a random process. This allows, in principle, one to fit sophisticated domain-specific models with easily interpretable parameters. However, the likelihood function in such models is typically intractable, and so likelihood-based inference techniques must deal with this intractability in some way. I will briefly introduce two simple likelihood-based methodologies, pseudo-marginal Markov chain Monte Carlo and simulated maximum likelihood, and comment on statistical and computational scalability in some example settings.
Dr. Anthony Lee is the Turing Programme Director for the data science at scale programme and will also provide an introduction to the Data Science at Scale programme at the Alan Turing Institute for Data Science.