Title: Beyond Generative Modeling with Measure Dynamics
Abstract: Transport-based models, such as diffusion or flow-matching, have become a leading framework for generative modeling, by reducing the task to learning conditional expectations under suitable “noise” semigroups. In this talk, we will describe how these models can be adapted beyond generative modeling to the setting of inverse problems. We will focus on two snippets: (i) performing provable posterior sampling in the context of linear inverse problems, and (ii) learning a generative model from corrupted measurements, akin to solving another linear inverse problem, this time in the space of distributions. Joint work with Jiequn Han, Chirag Modi and Eric Vanden-Eijnden.