Equipe ALEA Website

  • Increase font size
  • Default font size
  • Decrease font size

Biips: Bayesian inference with interacting particle systems

Print PDF

Please visit Biips Homepage


People: François Caron, Adrien Todeschini, Pierrick Legrand, Pierre Del Moral


Context: Bayesian inference consists in approximating an unknown parameter dependent conditional probability law given a set of observations. A large number of problems, e.g. non-supervised classification, filtering, etc., can be addressed having as basis the aforementioned formulation. The underlying probability law, while not calculable in analytical manner for the general case, can be approximated by using Monte Carlo Markov Chain (MCMC) methods. These methods are popular for bayesian inference thanks to BUGS software and the WinBUGS graphical interface.

Emerged as a result of recent research studies, interacting particle based algorithms - also known as Sequential Monte Carlo (SMC) methods in which the most common implementation is the particle filter - proved to have superior performances when compared to classical MCMC approaches. What is more, interacting particle algorithms are well adapted for dynamic estimation problems as encountered, for example, in filtering, tracking or classification problems. They do not require burn in convergence time and include calculation of the normalizing constant.


Objectives: General software for bayesian inference with interacting particle systems, i.e. SMC methods.

  • popularizing the use of these methods to researchers and students
  • user-friendly software : BUGS and JAGS users will be able to use their existing models into Biips

Similar software: BUGS and JAGS are general software for bayesian inference using Gibbs sampling, an MCMC simulation algorithm.


Development: Written in C++, the software comes along with an R package allowing to run Biips from R console and providing nice results analysis and plotting functions.

The software is under development.

A linux and windows release is coming soon.