Bayesian statistical inverse problems: statistical guarantees and polynomial-time computation

08.05.2026 11:15 – 12:15

RESEARCH INSTITUTE FOR STATISTICS AND INFORMATION SCIENCE SEMINARS

ABSTRACT

Bayesian and related methodologies have been extremely popular for estimation, prediction and inference in complex statistical models, for instance arising from differential equations (PDEs/SDEs). We present recent statistical and computational guarantees which underpin those methodologies. On the one hand, we will discuss statistical convergence theory towards the ‘ground truth’ as the statistical sample size increases. Secondly, we address recent progress in studying the computational complexity of the numerical algorithms required. This includes polynomial-time mixing results for high-dimensional Markov Chain Monte Carlo (MCMC) methods as well as recent “generalized M-estimators” introduced in https://arxiv.org/abs/2601.09007.

Lieu

Bâtiment: Uni Mail

Boulevard du Pont-d'Arve 40
1205 Geneva

Room M 4220, 4th floor

entrée libre