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

TL;DR

CaloFlow v2 is a significantly faster generative model for calorimeter shower simulation that maintains high fidelity, achieving a 10,000-fold speedup over traditional GEANT4 simulations using advanced normalizing flow techniques.

Contribution

We introduce CaloFlow v2, which employs Probability Density Distillation with new loss terms to drastically improve generation speed while preserving high accuracy.

Findings

CaloFlow v2 is 500 times faster than its predecessor.

The model achieves a 10,000-fold speedup over GEANT4.

High fidelity is maintained as shown by qualitative and quantitative metrics.

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.