Inductive Simulation of Calorimeter Showers with Normalizing Flows

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Buckley, Matthew R., Krause, Claudius, Pang, Ian, Shih, David
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929242563936256
author Buckley, Matthew R.
Krause, Claudius
Pang, Ian
Shih, David
author_facet Buckley, Matthew R.
Krause, Claudius
Pang, Ian
Shih, David
contents Simulating particle detector response is the single most expensive step in the Large Hadron Collider computational pipeline. Recently it was shown that normalizing flows can accelerate this process while achieving unprecedented levels of accuracy, but scaling this approach up to higher resolutions relevant for future detector upgrades leads to prohibitive memory constraints. To overcome this problem, we introduce Inductive CaloFlow (iCaloFlow), a framework for fast detector simulation based on an inductive series of normalizing flows trained on the pattern of energy depositions in pairs of consecutive calorimeter layers. We further use a teacher-student distillation to increase sampling speed without loss of expressivity. As we demonstrate with Datasets 2 and 3 of the CaloChallenge2022, iCaloFlow can realize the potential of normalizing flows in performing fast, high-fidelity simulation on detector geometries that are ~ 10 - 100 times higher granularity than previously considered.
format Preprint
id arxiv_https___arxiv_org_abs_2305_11934
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Inductive Simulation of Calorimeter Showers with Normalizing Flows
Buckley, Matthew R.
Krause, Claudius
Pang, Ian
Shih, David
Instrumentation and Detectors
Machine Learning
High Energy Physics - Experiment
High Energy Physics - Phenomenology
Data Analysis, Statistics and Probability
Simulating particle detector response is the single most expensive step in the Large Hadron Collider computational pipeline. Recently it was shown that normalizing flows can accelerate this process while achieving unprecedented levels of accuracy, but scaling this approach up to higher resolutions relevant for future detector upgrades leads to prohibitive memory constraints. To overcome this problem, we introduce Inductive CaloFlow (iCaloFlow), a framework for fast detector simulation based on an inductive series of normalizing flows trained on the pattern of energy depositions in pairs of consecutive calorimeter layers. We further use a teacher-student distillation to increase sampling speed without loss of expressivity. As we demonstrate with Datasets 2 and 3 of the CaloChallenge2022, iCaloFlow can realize the potential of normalizing flows in performing fast, high-fidelity simulation on detector geometries that are ~ 10 - 100 times higher granularity than previously considered.
title Inductive Simulation of Calorimeter Showers with Normalizing Flows
topic Instrumentation and Detectors
Machine Learning
High Energy Physics - Experiment
High Energy Physics - Phenomenology
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2305.11934