ML4Jets2024

Session

Detector Simulation

Nov 5, 2024, 4:00 PM

LPNHE, Paris, France

Conveners

Detector Simulation

• Claudius Krause (HEPHY Vienna (ÖAW))

Detector Simulation

• Sascha Diefenbacher (Lawrence Berkeley National Lab. (US))

Detector Simulation

• Timo Janssen

51. Generative transformers for learning point-cloud simulations

Henning Rose

11/5/24, 4:00 PM

We successfully demonstrate the use of a generative transformer for learning point-cloud simulations of electromagnetic showers in the International Large Detector (ILD) calorimeter. By reusing the architecture and workflow of the “OmniJet-alpha” model, this transformer predicts sequences of tokens that represent energy deposits within the calorimeter. This autoregressive approach enables the...

73. CaloDREAM -- Detector Response Emulation via Attentive flow Matching

Luigi Favaro

11/5/24, 4:20 PM

Detector simulations are an exciting application of modern generative networks. Their sparse high-dimensional data combined with the required precision poses a serious challenge. We show how combining Conditional Flow Matching with transformer elements allows us to simulate the detector phase space reliably. Namely, we use an autoregressive transformer to simulate the energy of each layer, and...

81. Higher Resolution and Angular Conditioning for Normalizing-Flow-based Generation of Calorimeter Showers

Thorsten Lars Henrik Buss (Universität Hamburg (DE))

11/5/24, 4:40 PM

Monte Carlo (MC) simulations are crucial for collider experiments, enabling the comparison of experimental data with theoretical predictions. However, these simulations are computationally demanding, and future developments, like increased event rates, are expected to surpass available computational resources. Generative modeling can substantially cut computing costs by augmenting MC...

20. Calo4pQVAE: A calorimeter surrogate for high energy particle-calorimeter interactions using Dwave’s Zephyr topology

J. Quetzalcoatl Toledo-Marin (TRIUMF)

11/5/24, 5:00 PM

One potential roadblock towards the HL-LHC experiment, scheduled to begin in 2029, is the computational demand of traditional collision simulations. Projections suggest current methods will require millions of CPU-years annually, far exceeding existing computational capabilities. Replacing the event showers module in calorimeters with quantum-assisted deep learning surrogates can help bridge...

30. BitHEP – Are 1-Bit Networks all we need?

Daohan Wang (HEPHY ÖAW)

11/5/24, 5:20 PM

With the rise of modern and complex neural network architectures, there is a growing need for fast and memory-efficient implementations to avoid computational bottlenecks in high-energy physics (HEP). We explore the performance of the BITNET architecture in state-of-the-art HEP applications, focusing on classification, regression and generative modeling tasks. Specifically, we apply BITNET to...

10. Fast Perfekt: Regression-based refinement of fast simulation

Lars Stietz (Hamburg University of Technology (DE))

11/6/24, 9:00 AM

As data sets grow in size and complexity, simulated data play an increasingly important role in analysis. In many fields, two or more distinct simulation software applications are developed that trade off with each other in terms of accuracy and speed. The quality of insights extracted from the data stand to increase if the accuracy of faster, more economical simulation could be improved to...

99. Refining CMS Fast Simulation with ML-based regression

Samuel Louis Bein (Universite Catholique de Louvain (UCL) (BE))

11/6/24, 9:20 AM

The CMS Fast Simulation chain (FastSim) is roughly 10 times faster than the application based on the GEANT4 detector simulation and full reconstruction referred to as FullSim. This advantage however comes at the price of decreased accuracy in some of the final analysis observables. A machine learning-based technique to refine those observables has been developed and its status is presented...

63. Faster Than Fast: Pushing the Limits of Simulation with Generative Models in HEP

Sitian Qian (Peking University (CN))

11/6/24, 9:40 AM

Fast event and detector simulation in high-energy physics using generative models provides a viable solution for generating sufficient statistics within a constrained computational budget, particularly in preparation for the High Luminosity LHC. However, many of these applications suffer from a quality/speed tradeoff. Diffusion models offer some of the best sampling quality but slow generation...

70. Parnassus: An Automated Approach to Accurate, Precise, and Fast Detector Simulation and Reconstruction

Dmitrii Kobylianskii (Weizmann Institute of Science (IL))

11/6/24, 10:00 AM

Simulating particle physics data is an essential yet computationally intensive process in analyzing data from the LHC. Traditional fast simulation techniques often use a surrogate calorimeter model followed by a reconstruction algorithm to produce reconstructed objects. In this work, we introduce Particle-flow Neural Assisted Simulations (Parnassus), a deep learning-based method for generating...

13. A Library for ML-based Fast Calorimeter Shower Simulation at Future Collider Experiments and Beyond

Peter McKeown (CERN)

11/7/24, 1:50 PM

Experiments at current and future colliders rely fundamentally on precise detector simulation. While traditional simulation approaches based on Monte Carlo techniques provide a high degree of physics fidelity, they place an enormous burden on the available computational resources. This is particularly true of particle showers created in the calorimeters, which have been a focus of fast...

17. Towards Detector Agnostic Fast Calorimetry Simulation

Piyush Raikwar (CERN)

11/7/24, 2:10 PM

Calorimeter simulations based on Monte Carlo methods (Geant4), while accurate, are computationally expensive and time-consuming. In this regard, numerous efforts aim to accelerate these simulations faster via generative machine learning. Although these machine learning models tend to be faster than Geant4, their design demands a significant amount of time, computational resources, and...

83. CaloClouds III: Ultra-Fast Geometry-Independent Highly-Granular Calorimeter Simulation

Anatolii Korol

11/7/24, 2:30 PM

Ever-increasing collision rates place significant computational stress on the simulation of future experiments in high energy physics. Generative machine learning (ML) models have been found to speed up and augment the most computationally intensive part of the traditional simulation chain: the calorimeter simulation. Many previous studies relied on fixed grid-like data representation of...

44. Point-Clouds based Diffusion Model on Hadronic Showers

Martina Mozzanica (Hamburg University (DE))

11/7/24, 2:50 PM

Simulating showers of particles in highly-granular detectors is a key frontier in the application of machine learning to particle physics. Achieving high accuracy and speed with generative machine learning models can enable them to augment traditional simulations and alleviate a major computing constraint.
Recent developments have shown how diffusion based generative shower simulation...