HTLR: Bayesian Logistic Regression with Heavy-Tailed Priors


Permission is granted for anyone to copy, use, modify, or distribute these programs and accompanying documents for any purpose, provided this copyright notice is retained and prominently displayed, and note is made of any changes made to these programs. These programs and documents are distributed without any warranty, express or implied. As the programs were written for research purposes only, they have not been tested to the degree that would be advisable in any important application. All use of these programs is entirely at the user's own risk.


HTLR performs classification and feature selection by fitting Bayesian multinomial logistic regression models based on heavy-tailed (hyper-LASSO, non-convex) priors with small degree freedom. The software is suitable for classification with high-dimensional features, such as gene expression profiles. With small scale, heavy-tailed priors can impose stronger shrinkage to the coefficients associated with a large number of useless features than Gaussian and Laplace priors do, but still allow coefficients of a small number of useful features to stand out with little punishment. Heavy-tailed priors can also automatically make selection within a large number of correlated features. The posterior of coefficients and hyper-parameters is sampled with restricted Gibbs sampling for leveraging the high-dimensionality and Hamiltonian Monte Carlo for handling the high-correlations among coefficients. The core computation in this software is carried out with fast C++ code.

Source Packages and Documentations


The methods used in this software are discussed in details in the following papers:

Instruction of Installing an R package and Using R

Click here for instruction of installing an R package and using R.