Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters
This work addresses the need for faster and more controllable simulations in high-energy physics, though it appears incremental by building on existing GAN-based acceleration methods.
The paper tackles the problem of conditioning generative adversarial networks (GANs) on physically meaningful attributes to accelerate simulations of particle showers in electromagnetic calorimeters, introducing an auxiliary training task that enables attribute-aware generation.
High-precision modeling of subatomic particle interactions is critical for many fields within the physical sciences, such as nuclear physics and high energy particle physics. Most simulation pipelines in the sciences are computationally intensive -- in a variety of scientific fields, Generative Adversarial Networks have been suggested as a solution to speed up the forward component of simulation, with promising results. An important component of any simulation system for the sciences is the ability to condition on any number of physically meaningful latent characteristics that can effect the forward generation procedure. We introduce an auxiliary task to the training of a Generative Adversarial Network on particle showers in a multi-layer electromagnetic calorimeter, which allows our model to learn an attribute-aware conditioning mechanism.