Bayesian imaging inverse problems with partially unknown modelsMS72

This talk presents a general Bayesian computation framework for performing inference in inverse problems with forward models that are partially unknown. A main novelty of the framework is that it uses MCMC-driven stochastic optimisation methods that tightly integrate modern high-dimensional Monte Carlo sampling and convex optimisation approaches. The proposed methodology is illustrated on a range of challenging imaging problems and compared to other techniques from the state of the art.

This presentation is part of Minisymposium “MS72 - Inverse problems with imperfect forward models (2 parts)
organized by: Yury Korolev (University of Cambridge) , Martin Burger (University of Muenster) .

Marcelo Pereyra (Harriott-Watt University)
bayesian methods, image reconstruction, inverse problems