Skip to yearly menu bar Skip to main content

Workshop: NeurIPS 2023 Workshop: Machine Learning and the Physical Sciences

Advancing Generative Modelling of Calorimeter Showers on Three Frontiers

Erik Buhmann · Sascha Diefenbacher · Engin Eren · Frank Gaede · Gregor Kasieczka · William Korcari · Anatolii Korol · Claudius Krause · Katja Krueger · Peter McKeown · Imahn Shekhzadeh · David Shih


Generative machine learning can be used to augment and speed-up traditional physics simulations, i.e. the simulation of elementary particles in the detector of collider experiments. Like many physics data, these calorimeter showers can either be represented as images or as permutation-invariant lists of measurements, i.e. as point clouds. We advance the generative models for calorimeter showers on three frontiers: (1) increasing the number of conditional features for precise energy- and angle-wise generation with the bounded bottleneck auto-encoder (BIB-AE), (2) improving generation fidelity using a normalizing flow model, dubbed "Layer-to-Layer-Flows" (L2LFlows), (3) developing a diffusion model for geometry-independent calorimeter point cloud scalable to O(1000) points, called CaloClouds, and distilling it into a consistency model for fast single-shot sampling.

Chat is not available.