Behavior of the Gibbs Sampler in the Imbalanced Case/Bias Correction from Daily Min and Max Temperature Measurements

IDS.190 Topics in Bayesian Modeling and Computation

*Note:  The speaker this week will give two shorter talks within the usual session

Title:  

Behavior of the Gibbs sampler in the imbalanced case

Abstract:  

Many modern applications collect highly imbalanced categorical data, with some categories relatively rare. Bayesian hierarchical models combat data sparsity by borrowing information, while also quantifying uncertainty. However, posterior computation presents a fundamental barrier to routine use; a single class of algorithms does not work well in all settings and practitioners waste time trying different types of MCMC approaches. This talk is motivated by an application to quantitative advertising in which we encountered extremely poor computational performance for common data augmentation MCMC algorithms but obtained excellent performance for adaptive Metropolis. To obtain a deeper understanding of this behavior, we give strong theory results on computational complexity in an infinitely imbalanced asymptotic regime. Our results show why the data augmentations methods work poorly.

Title: 

Bias correction from the daily min and the max temperature measurements.

Abstract: 

This will be a talk on an applied project, which involves a mix of modeling and obtaining MCMC samplers for a data set from the climate sciences.

===========

For more information and an up-to-date schedule, please see https://stellar.mit.edu/S/course/IDS/fa19/IDS.190/

**Taking IDS.190 satisfies the seminar requirement for students in MIT’s Interdisciplinary Doctoral Program in Statistics (IDPS), but formal registration is open to any graduate student who can register for MIT classes. And the meetings are open to any interested researcher.   Talks will be followed by 30 minutes of tea/snacks and informal discussion.**