Lisa Gaedke Merzhauser - Recent Developments in the INLAverse: Bayesian Inference for Latent Gaussian Models

par Dr Lisa Gaedke Merzhauser

jeudi 21 mai 2026, 13:00 → 14:00 Europe/Paris

amphi Louis (ISPED)

Speaker: Lisa Gaedke Merzhauser from KAUST

Title: Recent Developments in the INLAverse: Bayesian Inference for Latent Gaussian Models

Abstract: The methodology of integrated nested Laplace approximations (INLA) offers fast and accurate Bayesian inference for the class of latent Gaussian models. In this talk, I will give a brief overview of INLA and its applicable model class, before diving into some recent developments. These include the extension to new model classes and improvements in computational performance through a new sparse linear solver for the R-INLA package. Further, I will introduce DALIA, a new standalone Python implementation of INLA, which was designed to run on your laptop as well as on hundreds of GPUs simultaneously, and illustrate its use in a large-scale air pollution study.

Calendar subscription link for the complete seminar series:
https://indico.math.cnrs.fr/category/711/events.ics

Program of the Biostatistics seminars:
https://indico.math.cnrs.fr/category/711/

Subscribe to the seminar mailing list:
https://diff.u-bordeaux.fr/sympa/subscribe/seminaire.biostat.bph

Former e-seminars on our YouTube channel (mostly in French): https://www.youtube.com/channel/UCURp-hEQL7k23UzGfqgEurA/videos

 

Biostatistics seminar series from the Department of Public Health from the University of Bordeaux and the Bordeaux Population Health UMR 1219 research center