EF Learning-Informed Optimization

Generative neural models based on flows in measure spaces have shown a large impact on applications. However, the velocity fields learned by neural networks may lack a certain continuity which leads to undesired effects in neural approximations. This project aims to examine the behavior of such velocity fields theoretically and to use our insights towards the modeling of other physics-inspired generative flow models. A unifying framework of certain physics-inspired approaches are operator semigroups.