University of Cambridge > > Isaac Newton Institute Seminar Series > Optimisation and complexity for Gibbs samplers for hierarchical and crossed-effect models

Optimisation and complexity for Gibbs samplers for hierarchical and crossed-effect models

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact INI IT.

SINW01 - Scalable statistical inference

We study the convergence properties of the Gibbs Sampler in the context of Gaussian hierarchical and crossed-effect models. We develop a novel methodology based on multi-grid decompositions to derive analytic expressions for the convergence rates of the algorithm, extending significantly the class of conditionally Gaussian models amenable to direct analysis. In the hierarchical context, our work gives a rather complete understanding of the Gibbs Sampler behaviour for symmetric models (with arbitrary depth), while providing approximations and bounds for the non-symmetric cases. The theoretical results give rise to simple and easy-to-implement guidelines to optimise practical implementations of the Gibbs samplers on such models. While the good performances of the Gibbs Sampler in hierarchically-structured models is renowned, the context of crossed-effect models is drastically different. Here hierarchical centering is not possible and the convergence of commonly implemented Gibbs Sampler strategies deteriorates as the data-size increases, resulting in super-linear computational complexity (potentially even quadratic) in the number of data-points. We show how to leverage the negatively-correlated structure of crossed-effect models to design easy-to-implement collapsed Gibbs Samplers whose complexity matches the one of hierarchical scenarios. 

This is joint work with Giacomo Zanella and Omiros Papaspiliopoulos.  

This talk is part of the Isaac Newton Institute Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity