CaloFlow II: Even Faster and Still Accurate Generation of Calorimeter Showers with Normalizing Flows

Abstract

Recently, we introduced CaloFlow, a high-fidelity generative model for GEANT4 calorimeter shower emulation based on normalizing flows. Here, we present CaloFlow v2, an improvement on our original framework that speeds up shower generation by a further factor of 500 relative to the original. The improvement is based on a technique called Probability Density Distillation, originally developed for speech synthesis in the ML literature, and which we develop further by introducing a set of powerful new loss terms. We demonstrate that CaloFlow v2 preserves the same high fidelity of the original using qualitative (average images, histograms of high level features) and quantitative (classifier metric between GEANT4 and generated samples) measures. The result is a generative model for calorimeter showers that matches the state-of-the-art in speed (a factor of $10^4$ faster than GEANT4) and greatly surpasses the previous state-of-the-art in fidelity.

arXiv comment24 pages, 15 figures, 4 tables; v2: matches accepted version

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• On Calibration of Modern Neural Networks
• Normalizing Flows: An Introduction and Review of Current Methods
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Normalizing Flows for Probabilistic Modeling and Inference
• MADE: Masked Autoencoder for Distribution Estimation
• Masked Autoregressive Flow for Density Estimation
• Improving Variational Inference with Inverse Autoregressive Flow
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Decoding Photons: Physics in the Latent Space of a BIB-AE Generative Network
• Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters
• ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
• The CMS HGCAL detector for HL-LHC upgrade
• Distilling the Knowledge from Conditional Normalizing Flows

Cited by in corpus (4)

• MadNIS -- Neural Multi-Channel Importance Sampling
• CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Ephemeral Learning -- Augmenting Triggers with Online-Trained Normalizing Flows