CaloFlow II: Even Faster and Still Accurate Generation of Calorimeter Showers with Normalizing Flows
This work improves simulation efficiency for particle physics researchers, but it is incremental as it builds on their prior CaloFlow model.
The authors tackled the problem of generating calorimeter showers for particle physics simulations, achieving a 500x speedup over their previous model while maintaining high fidelity, resulting in a generative model that is 10^4 times faster than GEANT4 and surpasses previous state-of-the-art in fidelity.
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.