Week 5: Bayesian Statistics and Algorithms

February 29 – March 4, 2016
This week will take place during the Thematic Month on « Statistics » at CIRM (Marseille, France). It will be devoted to Bayesian statistics as well as  their associated algorithms.
Theoretical presentations and applications on these two themes will be developed. Mini courses will also take place and theoretical and applied aspects of the Bayesian approach will be presented. The algorithms will include ABC (Approximate Bayesian Computation) and MCMC algorithms.

Some key words regarding this workshop:

– Bayesian statistics (courses and lectures)
– ABC algorithm (courses and lectures)
– MCMC algorithms (lectures and presentations)
– Applications
– Big data (and Bayesian algorithms)
– Variational algorithms (Variational Bayes, Expectation Propagation)
– Sequential Monte Carlo algorithms (a.k.a. particle filters)

Note: all talks and mini-courses will be in English

Scientific Committee

Nicolas Chopin (ENSAE ParisTech)
Gilles Celeux  (Inria Paris)

Organizing Committee

Thibaut Le Gouic (Ecole Centrale de Marseille)
Denys Pommeret (Aix-Marseille Université)
Thomas Willer (Aix-Marseille Université)


I) Mini-courses

Expectation-Propagation for Approximate Inference

Variational Bayes methods and algorithms

Computational Bayesian statistics

II) Talks

Bayesian hierarchical mixture model for financial time series

Leave Pima Indians alone: binary regression as a benchmark for Bayesian computation

Expectation Propagation is exact in the large-data limit

Convergence modes for prior distributions

An overview of noisy MCMC and SMC

Accelerating Bayesian inference for intractable likelihood models using noisy MCMC

Goodness of fit of logistic models for random graphs

Combining  ridge parameter with the g-prior of Zellner

A data augmentation approach to high dimensional ABC

Adaptive multiple important sampling

Exploring the presence of complex dependence structures in epidemiological and genomic data

On the properties of variational approximations of Gibbs posteriors

Exact Bayesian inference for some models with discrete parameters

Nonparametric mixture models and HMMS

Approximations of geometrically ergodic Markov chains

Computational methods for stochastic differential equations

Bayesian Hierarchical Modelling of Genetic Interaction in Yeast