Login

CaloChallenge Workshop

30–31 May 2023
Villa Mondragone
Europe/Rome timezone

Contribution List

31 out of 31 displayed
Export to PDF
  1. 12. Bus at piazza Marconi
    30/05/2023, 08:30

    Bus will leave at 9:00 for Villa Mondragone

    Go to contribution page
  2. 13. Registration
    30/05/2023, 09:30
  3. 14. Introduction
    Michele Faucci Giannelli (Istituto Nazionale di Fisica Nucleare)
    30/05/2023, 10:00
  4. 15. Welcome from INFN Tor Vergata
    Anna Di Ciaccio (Istituto Nazionale di Fisica Nucleare)
    30/05/2023, 10:05
  5. 32. Welcome from Fellini
    LAURA BANDIERA (Istituto Nazionale di Fisica Nucleare)
    30/05/2023, 10:10
  6. 16. ML in industry
    Serena Palazzo (CS)
    30/05/2023, 10:15
  7. 17. CaloShowerGAN
    Michele Faucci Giannelli (Istituto Nazionale di Fisica Nucleare), Rui Zhang
    30/05/2023, 11:00
  8. 18. MDMA-GAN
    Benno Käch (Deutsches-Elektronen Synchrotron (DESY))
    30/05/2023, 11:30
  9. 19. BolognaGAN: a containerized solution
    Federico Andrea Guillaume Corchia (Istituto Nazionale di Fisica Nucleare)
    30/05/2023, 12:00
  10. 20. Discussion
    30/05/2023, 12:30
  11. 10. Latent Generative Models for Calo Simulation with VQ-VAE
    Qibin LIU (TDLI., Shanghai JiaoTong University)
    30/05/2023, 14:00

    Simulation of calorimeter response is important for modern high energy physics experiments. With increasingly large and high granularity design of calorimeters, the computational cost of conventional MC-based simulation of each particle-material interaction is becoming a major bottleneck.

    We propose a new generative model based on a two-stage generative model which is similar to recently...

    Go to contribution page
  12. 29. CERN-Geneva VAE
    Dalila Salamani (CERN)
    30/05/2023, 14:30
  13. 2. CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds
    Humberto Alonso Reyes Gonzalez (Istituto Nazionale di Fisica Nucleare)
    30/05/2023, 15:00

    The efficient simulation of particle propagation and interaction within the detectors of the Large Hadron Collider (LHC) is of primary importance for precision measurements and new physics searches. The most computationally expensive simulations involve calorimeter showers, which will become ever more costly and high-dimensional as the Large Hadron Collider moves into its High Luminosity era. ...

    Go to contribution page
  14. 30. Discussion
    30/05/2023, 15:30
  15. 1. Score-based Generative Models for Calorimeter Shower Simulation
    Vinicius Mikuni (LBNL)
    30/05/2023, 16:30

    Diffusion generative models are a new class of generative algorithms that have been shown to produce realistic images even in high dimensional spaces, currently surpassing other state-of-the-art models for different benchmark categories and applications. In this work we introduce CaloScore, a score-based generative model for collider physics applied to calorimeter shower generation. Three...

    Go to contribution page
  16. 3. Denoising Diffusion Models for High Fidelity Calorimeter Simulation
    Oz Amram (Fermilab)
    30/05/2023, 17:00

    Denoising diffusion models have recently become state of the art in the ML community because of their stable training procedure and ability to generate high quality images in reasonable computation times. We employ diffusion models for the task of generating calorimeter showers within the context of the CaloChallenge. Our diffusion models are based on 3D cylindrical convolutional networks,...

    Go to contribution page
  17. 11. CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
    Anatolii Korol (Deutsches Elektronen-Synchrotron (DESY))
    30/05/2023, 17:30

    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 would enable them to augment traditional simulations and alleviate a major computing constraint.
    This work achieves a major breakthrough in this task by for the first time directly...

    Go to contribution page
  18. 31. Discussion
    30/05/2023, 18:00
  19. 21. Bus to dinner
    30/05/2023, 19:00
  20. 22. Bus at piazza Marconi
    31/05/2023, 08:30
  21. 4. (inductive) CaloFlow
    Ian Pang (Rutgers University)
    31/05/2023, 09:30

    We apply CaloFlow to GEANT4 showers of Dataset 1, producing high-fidelity samples with a sampling time of less than 0.1ms per shower. We validated the fidelity of the samples using multiple metrics, including a classifier metric. To generalize CaloFlow to the higher dimensional Datasets 2 and 3, we propose a new approach called Inductive CaloFlow. This approach involves training the flow on...

    Go to contribution page
  22. 8. Generating Accurate Showers in Highly Granular Calorimeters Using Normalizing Flows
    Thorsten Buss (University of Hamburg)
    31/05/2023, 10:00

    Normalizing flows are a type of generative models that can be trained directly by minimizing the negative log-likelihood. It has been shown that flows can accurately model showers in low complexity calorimeters. We show how normalizing flows can be improved and adapted to accurately model showers in calorimeters with significantly higher complexity. One of the key points here is to move away...

    Go to contribution page
  23. 6. CaloPointFlow - Generating Calorimeter Showers as Point Clouds
    Simon Schnake (DESY / RWTH Aachen)
    31/05/2023, 11:00

    In particle physics, precise simulations of the interaction processes in calorimeters are essential for scientific discovery. However, accurate simulations using GEANT4 are computationally very expensive and pose a major challenge for the future of particle physics. In this study, we apply the CaloPointFlow model, a novel generative model based on normalizing flows, to fast and high-fidelity...

    Go to contribution page
  24. 28. Discussion
    31/05/2023, 11:30
  25. 23. Going into production, FastCalo in the bigger picture
    Michele Faucci Giannelli (Istituto Nazionale di Fisica Nucleare)
    31/05/2023, 12:00
  26. 24. CaloChallenge result
    Claudius Krause (Heidelberg University)
    31/05/2023, 12:20
  27. 25. Discussion
    31/05/2023, 12:40
  28. 26. Bus depart to Frascati
    31/05/2023, 14:40
  29. 9. A containerized solution for fast calorimeter simulation
    Federico Andrea Guillaume Corchia (Istituto Nazionale di Fisica Nucleare), Lorenzo Rinaldi (Istituto Nazionale di Fisica Nucleare)

    The simulation of electromagnetic and hadronic interactions in calorimeters is a very demanding process, both in terms of time and computing resources. A novel technique based on Generative Adversarial Networks (GANs) may benefit from a more efficient use of computing resources, although initial training could be computationally demanding. Nowadays and in the near future we expect to have more...

    Go to contribution page
  30. 27. CaloScore
    Vinicius Mikuni (LBNL)
  31. 7. CANADA-GAN (acronym and name subject to possible future change, please excuse)
    Benno Käch (Deutsches-Elektronen Synchrotron (DESY))

    We propose the application of our previously published Cross AtteNtion meAn-fielD mAtching CANADA-GAN for generating particle showers in high-granularity datasets. Results are presented for dataset 2 and 3. Point cloud generative models are known to benefit from higher granularity, making these datasets well-suited for high-granularity calorimeters. Although the regular architecture of the...

    Go to contribution page