Speaker
Erik Buhmann
(University of Hamburg)
Description
Generative machine learning models allow fast event generation, yet are so far primarily constrained to fixed data and detector geometries.
We introduce a Deep Sets-based permutation equivariant generative adversarial network (GAN) for generating point clouds with variable cardinality - a flexible data structure optimal for collider events such as jets. The generator utilizes an interpretable global latent vector and does not rely on pairwise information sharing between particles, leading to a significant speed-up over graph-based approaches
Primary authors
Erik Buhmann
(University of Hamburg)
Gregor Kasieczka
(UNI/EXP (Uni Hamburg, Institut fur Experimentalphysik))
