
A Markov Chain MonteCarlo Approach to DoseResponse Optimization Using Probabilistic Programming (RStan)
A hierarchical logistic regression Bayesian model is proposed and implem...
read it

Block Gibbs samplers for logistic mixed models: convergence properties and a comparison with full Gibbs samplers
Logistic linear mixed model (LLMM) is one of the most widely used statis...
read it

Bayesian Inversion of Lognormal Eikonal Equations
We study the Bayesian inverse problem for inferring the lognormal slown...
read it

Bayesian inference of Stochastic reaction networks using Multifidelity Sequential Tempered Markov Chain Monte Carlo
Stochastic reaction network models are often used to explain and predict...
read it

Scalable Bayesian Nonparametric Clustering and Classification
We develop a scalable multistep Monte Carlo algorithm for inference und...
read it

Efficient posterior sampling for highdimensional imbalanced logistic regression
Highdimensional data are routinely collected in many application areas....
read it

A Note on Bayesian Modeling Specification of Censored Data in JAGS
Just Another Gibbs Sampling (JAGS) is a convenient tool to draw posterio...
read it
Multilevel Gibbs Sampling for Bayesian Regression
Bayesian regression remains a simple but effective tool based on Bayesian inference techniques. For largescale applications, with complicated posterior distributions, Markov Chain Monte Carlo methods are applied. To improve the wellknown computational burden of Markov Chain Monte Carlo approach for Bayesian regression, we developed a multilevel Gibbs sampler for Bayesian regression of linear mixed models. The level hierarchy of data matrices is created by clustering the features and/or samples of data matrices. Additionally, the use of correlated samples is investigated for variance reduction to improve the convergence of the Markov Chain. Testing on a diverse set of data sets, speedup is achieved for almost all of them without significant loss in predictive performance.
READ FULL TEXT
Comments
There are no comments yet.