Unifying Simulation and Inference with Normalizing Flows

TL;DR

This paper introduces a unified approach using normalizing flows and maximum likelihood estimation to improve detector calibration and simulation, enabling prior-independent energy regression with non-Gaussian resolution modeling.

Contribution

It presents a novel method that unifies detector calibration and simulation tasks through conditional generative models based on normalizing flows.

Findings

Demonstrates the approach with ATLAS-like calorimeter simulation

Shows non-Gaussian resolution modeling from likelihood shape

Achieves prior-independent energy regression

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.