Invertible Neural Networks for Inverse Problems

  • Sebastian Neumayer (TU Berlin)
E1 05 (Leibniz-Saal)


In this talk, I will discuss invertible neural networks, which can be used for modelling inverse problems. If properly trained, such networks provide a way for efficiently sampling from the posterior. Starting from the theoretical analysis of the related optimization problem, we will discuss some practical implications of the established results based on numerical examples. At the end, I will outline some open issues.