Current browse context:
hep-ph
Change to browse by:
References & Citations
High Energy Physics - Phenomenology
Title: Unifying Simulation and Inference with Normalizing Flows
(Submitted on 29 Apr 2024 (v1), last revised 9 May 2024 (this version, v2))
Abstract: There have been many applications of deep neural networks to detector calibrations and a growing number of studies that propose deep generative models as automated fast detector simulators. We show that these two tasks can be unified by using maximum likelihood estimation (MLE) from conditional generative models for energy regression. Unlike direct regression techniques, the MLE approach is prior-independent and non-Gaussian resolutions can be determined from the shape of the likelihood near the maximum. Using an ATLAS-like calorimeter simulation, we demonstrate this concept in the context of calorimeter energy calibration.
Submission history
From: Ian Pang [view email][v1] Mon, 29 Apr 2024 18:00:00 GMT (464kb,D)
[v2] Thu, 9 May 2024 21:41:49 GMT (460kb,D)
Link back to: arXiv, form interface, contact.