Speaker
Description
Simulation is the crucial connection between particle physics theory and experiment. Our ability to simulate particle collision based on first principles allows us to analyze and understand the vast amount of data of the Large Hadron Collider (LHC) experiments. This, however, comes at a cost: A lot of computational resources are needed to simulate all necessary interactions to the required precision.
In recent years, deep generative models have shown great performance as fast and faithful surrogate models and in improving Monte Carlo-based importance sampling. In my talk, I will give an overview on the use of deep generative models in particle physics. I will introduce the main architectures and their advantages and disadvantages in terms of speed and precision. I will also talk about how deep generative models can be evaluated to ensure they have the precision we require for particle physics.
