Quotation Winkler, Daniel, Adelsberger, Stephan, Frühwirth-Schnatter, Sylvia. 2021. A New Domain-Specific Language for MCMC Inference. European Seminar on Bayesian Econometrics, Virtual, Spain, 08.09.-09.09.


RIS


BibTeX

Abstract

The development of MCMC algorithms involves an implementation in a mathematical language, in addition to one in a programming language. Often a third version is written in a faster, lower-level language (e.g., R with C++). This development cycle comes with obvious drawbacks. It requires a separate manual code “translation” for each programming language, which may lead to errors and does not scale. Our contribution is a system for MCMC algorithms based on a newly developed domain-specific language (DSL). DSLs are special-purpose languages, designed for one narrow task (e.g., SQL). Our DSL allows the implementation of algorithms using mathematical notation, which is then translated to the users’ preferred languages, e.g., R, Julia, or MATLAB. Our newly developed DSL constitutes a concise, easily comprehensible, and extensible yet powerful system to streamline MCMC development. While researchers retain complete control over the algorithm, highly optimized backends (e.g. GPU) can be provided by domain specialists. In the full paper, we will showcase the DSL implementation of multiple MCMC algorithms based on global-local shrinkage priors (Gibbs, Metropolis within Gibbs, etc.). We demonstrate that the same model can be compiled to R, Julia, and MATLAB code.

Tags

Press 'enter' for creating the tag

Publication's profile

Status of publication Published
Affiliation WU
Type of publication Poster presented at an academic conference or symposium
Language English
Title A New Domain-Specific Language for MCMC Inference
Event European Seminar on Bayesian Econometrics
Date 08.09.-09.09
Location Virtual
Country Spain
Year 2021
URL http://www.est.uc3m.es/BayesUC3M/ESOBE2021/ESOBE2021.htm

Associations

People
Winkler, Daniel (Details)
Adelsberger, Stephan (Details)
Frühwirth-Schnatter, Sylvia (Details)
Organization
Institute for Retailing & Data Science IN (Details)
Google Scholar: Search