Machine learning has found many uses in high energy physics (HEP), and this talk will focus on normalizing flows and foundation models in this context. We will discuss what a normalizing flow is, how it differs from other popular generative models, and how they can be used to interpolate distributions, learn optimal transport maps, and remove bias from classifier decisions. The talk will also discuss foundation models, how they can be developed for physics experiments and the benefits they offer over traditional approaches.
Zoom: https://stanford.zoom.us/j/94336961522?pwd=baYrOxqHhyGeExE9MGbzdVV0oSlJgM.1