Refining Fast Calorimeter Simulations with a Schrödinger Bridge
arXiv:2308.12339
Abstract
Machine learning-based simulations, especially calorimeter simulations, are promising tools for approximating the precision of classical high energy physics simulations with a fraction of the generation time. Nearly all methods proposed so far learn neural networks that map a random variable with a known probability density, like a Gaussian, to realistic-looking events. In many cases, physics events are not close to Gaussian and so these neural networks have to learn a highly complex function. We study an alternative approach: Schrödinger bridge Quality Improvement via Refinement of Existing Lightweight Simulations (SQuIRELS). SQuIRELS leverages the power of diffusion-based neural networks and Schrödinger bridges to map between samples where the probability density is not known explicitly. We apply SQuIRELS to the task of refining a classical fast simulation to approximate a full classical simulation. On simulated calorimeter events, we find that SQuIRELS is able to reproduce highly non-trivial features of the full simulation with a fraction of the generation time.
10 pages, 5 figures, version 2: updated conclusion for journal submission
Cited by in corpus (10)
- The MadNIS Reloaded
- CaloDREAM -- Detector Response Emulation via Attentive flow Matching
- Precision-Machine Learning for the Matrix Element Method
- Normalizing Flows for High-Dimensional Detector Simulations
- Differentiable MadNIS-Lite
- Full Event Particle-Level Unfolding with Variable-Length Latent Variational Diffusion
- Generative Unfolding with Distribution Mapping
- Extrapolating Jet Radiation with Autoregressive Transformers
- BitHEP -- The Limits of Low-Precision ML in HEP
- Fast Perfekt: Regression-based refinement of fast simulation