Choose timezone
Your profile timezone:
Abstract: Generative models offer a great deal of flexibility in a wide range of domains, in particular for fast generation and surrogate models. However, in high energy physics a lot of challenges arise from the modelling of distributions, and extracting sensitivity from non-deterministic processes. Here, generative models offer alternatives to standard analysis techniques often used for regression, interpolation, and calibration, to name a few. In this talk I will present several techniques in which we exploit conditional normalizing flows for regression, domain shift, and super resolution, all within the context of high energy physics.
ODSL Seminar Organization Team