Name: 5th Inter-experiment Machine Learning Workshop
Start: 2022-05-09T09:00:00+02:00
End: 2022-05-13T18:10:00+02:00
Location: CERN

5th Inter-experiment Machine Learning Workshop

from Monday 9 May 2022 (09:00) to Friday 13 May 2022 (18:10)

Monday 9 May 2022

12:00 Lunch Break
Lunch Break
12:00 - 14:00
Room: 500/1-001 - Main Auditorium

14:00 CANCELLED, we begin at 15:30 (was: CERN ML Resources)
CANCELLED, we begin at 15:30 (was: CERN ML Resources)
14:00 - 15:00
Room: 500/1-001 - Main Auditorium

15:00 Coffee Break
Coffee Break
15:00 - 15:30
Room: 500/1-001 - Main Auditorium
15:30 JAX and Differentiable Programming
JAX and Differentiable Programming
15:30 - 18:00
Room: 500/1-001 - Main Auditorium
Contributions

15:30 JAX and Differentiable Programming Tutorial - Lukas Alexander Heinrich (CERN) Nathan Daniel Simpson (Lund University (SE))
Tuesday 10 May 2022
09:00
09:00 - 09:10
Room: 500/1-001 - Main Auditorium
Contributions

09:00 Opening of the workshop - Andrea Wulzer (CERN and EPFL) Anja Butter David Rousseau (IJCLab-Orsay) Fabio Catalano (University and INFN Torino (IT)) Gian Michele Innocenti (CERN) Lorenzo Moneta (CERN) Michael Aaron Kagan (SLAC National Accelerator Laboratory (US)) Pietro Vischia (Universite Catholique de Louvain (UCL) (BE)) Riccardo Torre (CERN) Simon Akar (University of Cincinnati (US))
09:10
09:10 - 12:10
Room: 500/1-001 - Main Auditorium
Contributions

09:10 Future applications of ML in HEP - Tommaso Dorigo (Universita e INFN, Padova (IT))

10:00 ML in Cosmology - Christoph Weniger (University of Amsterdam)

11:20 Quantum ML - Sofia Vallecorsa (CERN)
12:10 Lunch Break
Lunch Break
12:10 - 13:30
Room: 500/1-001 - Main Auditorium
13:30 Invited contribution
Invited contribution
13:30 - 14:15
Room: 500/1-001 - Main Auditorium
Contributions

13:30 Differentiable Physics Simulations for Deep Learning - Nils Thürey (Technische Universität München)
14:15
14:15 - 15:35
Room: 500/1-001 - Main Auditorium
Contributions

14:15 How to drive scientific progress with community-driven open source projects: the scikit-learn approach - Alexandre Gramfort (INRIA, Univ. Paris Saclay)

14:55 Hardware and software challenges for massive-scale AI - Laurent Daudet (CTO and co-founder at LightOn, Professor (on leave) of physics at Université de Paris. )
15:35 Coffee Break
Coffee Break
15:35 - 16:05
Room: 500/1-001 - Main Auditorium
16:05 Jets and simulations
Jets and simulations
16:05 - 18:05
Room: 500/1-001 - Main Auditorium
Contributions

16:05 Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders - Breno Orzari (UNESP - Universidade Estadual Paulista (BR))

16:20 Hadrons, Better, Faster, Stronger - Engin Eren

16:45 SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics. - Atul Kumar Sinha (University of Geneva)

17:10 Calibrating stochastic simulations with optimal transport - Philipp Windischhofer (University of Oxford (GB))
Wednesday 11 May 2022
09:00 Uncertainty-aware learning, invertible networks, and anomaly detection in DQM
Uncertainty-aware learning, invertible networks, and anomaly detection in DQM
09:00 - 10:30
Room: 4/3-006 - TH Conference Room
Contributions

09:00 Conditional Invertible Network for Neutrino Regression - Matthew Leigh (University of Geneva)

09:25 Uncertainty Aware Learning for High Energy Physics With A Cautionary Tale - Aishik Ghosh (University of California Irvine (US))

09:30 Learning New Physics aware of systematic uncertainties - Gaia Grosso (Universita e INFN, Padova (IT))

09:45 Learning Optimal Test Statistics in the Presence of Nuisance Parameters - Lukas Alexander Heinrich (CERN)

10:00 Spatio-Temporal Anomaly Detection for the DQM of the CMS Experiment via Graph Networks - Mulugeta Asres (University of Agder (NO))
10:30 Coffee Break
Coffee Break
10:30 - 11:00
Room: 500/1-001 - Main Auditorium
11:00 CERN Data Science Seminar - Coline Devin (Deep Mind)
CERN Data Science Seminar
- Coline Devin (Deep Mind)
11:00 - 11:50
Room: 500/1-001 - Main Auditorium Agenda and zoom connection are dedicated to this seminar (different from the zoom room of the workshop)
11:50 Discussion
Discussion
11:50 - 12:00
Room: 500/1-001 - Main Auditorium

12:00 Lunch Break
Lunch Break
12:00 - 14:00
Room: 500/1-001 - Main Auditorium
14:00 Foundation models (IBM)
Foundation models (IBM)
14:00 - 15:00
Room: 500/1-001 - Main Auditorium
Contributions

14:00 Foundation Models for Accelerated Discovery - John R. Smith ( IBM Fellow and IBM Research global lead for Discovery Technology Foundations)
15:00 Neural ratio estimators, Autoencoders, Orsay workshop summary
Neural ratio estimators, Autoencoders, Orsay workshop summary
15:00 - 16:00
Room: 500/1-001 - Main Auditorium
Contributions

15:00 Truncated Marginal Neural Ratio Estimation with swyft - Benjamin Kurt Miller (University of Amsterdam)

15:25 Summary of Learning To Discover workshop - David Rousseau (IJCLab-Orsay)

15:50 Autoencoders for semivisible jet detection - Jeremi Niedziela (ETH Zurich (CH))

15:55 Invariant Representation Driven Neural Classifier for Anti-QCD Jet Tagging - Taoli Cheng (University of Montreal)
16:00 Coffee Break
Coffee Break
16:00 - 16:30
Room: 500/1-001 - Main Auditorium
16:30 Simulation-based inference, neural ratio estimates, end-to-end reconstruction, anomaly detection
Simulation-based inference, neural ratio estimates, end-to-end reconstruction, anomaly detection
16:30 - 18:15
Room: 500/1-001 - Main Auditorium
Contributions

16:30 Cosmological Simulation-Based Inference with Truncated Marginal Neural Ratio Estimation - Alex Cole

16:55 CURTAINs for you Sliding Window: Constructing Unobserved Regions by Transporting Adjacent INtervals to improve the reach of bump hunts in the search for new physics - Debajyoti Sengupta (Universite de Geneve (CH))

17:20 Object condensation for end-to-end reconstruction in high occupancy calorimeters with graph neural networks - Shah Rukh Qasim (Manchester Metropolitan University (GB))

17:45 Anomaly detection for the quality control of silicon sensor wafers for the CMS HGCAL upgrade - Sonja Grönroos (University of Helsinki (FI))

18:00 Clustering for interpreting complex high-energy physics models - Walter Hopkins (Argonne National Laboratory (US))
Thursday 12 May 2022
09:00 Generative Models
Generative Models
09:00 - 10:10
Room: 4/3-006 - TH Conference Room
Contributions

09:00 Calomplification: The Power of Generative Calorimeter Models - Sebastian Guido Bieringer (Hamburg University)

09:25 How to generate all possible simulations with GANs? - Jan Michal Dubinski (Warsaw University of Technology (PL))

09:30 Information-theoretic stochastic contrastive conditional GAN (InfoSCC-GAN) for physical data generation - Vitaliy Kinakh (Université de Genève (CH))

09:55 IEA-GAN: Intra-Event Aware GAN for the Fast Simulation of PXD Background at Belle II - Hosein Hashemi (LMU Munich)
10:10 Coffee Break
Coffee Break
10:10 - 10:35
Room: 500/1-001 - Main Auditorium
10:35 ML in theory and phenomenology
ML in theory and phenomenology
10:35 - 12:10
Room: 500/1-001 - Main Auditorium
Contributions

10:35 An infra-red and collinear safe message passing neural network - Vishal Singh Ngairangbam

11:00 Quarks and gluons in the Lund plane - Adam Takacs (University of Bergen) Frederic Alexandre Dreyer (University of Oxford) Gregory Soyez (IPhT, CEA Saclay)

11:15 Targeting Multi-Loop Integrals with Neural Networks - Ramon Winterhalder (UC Louvain)

11:40 Towards a Deep Learning Model for Hadronization - Andrzej Konrad Siodmok (Jagiellonian University (PL))

12:05 Using Machine Learning techniques in phenomenological studies in flavour physics - Jorge Alda Gallo (Universidad de Zaragoza)
12:10 Lunch Break
Lunch Break
12:10 - 13:30
Room: 500/1-001 - Main Auditorium
13:30 Generative models, and identification algorithms
Generative models, and identification algorithms
13:30 - 15:10
Room: 500/1-001 - Main Auditorium
Contributions

13:30 Turbo-Sim: a generalised generative model with a physical latent space - Guillaume Quétant (Université de Genève (CH))

13:55 Funnels: Exact maximum likelihood with dimensionality reduction - Samuel Byrne Klein (Universite de Geneve (CH))

14:20 ML-based Correction to Accelerate Geant4 Calorimeter Simulations - Evangelos Kourlitis (Argonne National Laboratory (US))

14:25 Particle identification with machine learning in ALICE Run 3 - Maja Kabus (Warsaw University of Technology (PL))

14:50 Data-driven machine learning algorithms for the calibration of space-charge distortion fluctuations in the ALICE TPC - Marian Ivanov (GSI - Helmholtzzentrum fur Schwerionenforschung GmbH (DE))
15:10 Coffee Break
Coffee Break
15:10 - 15:40
Room: 500/1-001 - Main Auditorium
15:40 Fast and real-time inference
Fast and real-time inference
15:40 - 17:00
Room: 4/3-006 - TH Conference Room
Contributions

15:40 FPGA acceleration of the CMS DNN based LLP Jet Algorithm for the LHC High-Luminosity upgrade - Tarik Ourida

16:05 Ephemeral Learning - Augmenting Triggers with Online-Trained Normalizing Flows - Sascha Daniel Diefenbacher (Hamburg University (DE))

16:20 Optimized Deep Learning Inference on High Level Trigger at the LHC: Computing time and Resource assessment - Syed Anwar Ul Hasan (Universita & INFN Pisa (IT))

16:35 Unsupervised learning for real-time SUEP detection in a High Level Trigger system at the LHC - Simranjit Singh Chhibra (CERN)

16:40 Neural network based primary vertex reconstruction with FPGAs for the upgrade of the CMS level-1 trigger system - Matthias Komm (Deutsches Elektronen-Synchrotron (DE))

16:55 Multi-objective optimization for the CMS High Granularity Calorimeter Level 1 trigger - Alexandre Hakimi (Centre National de la Recherche Scientifique (FR))
17:00

17:00 - 19:00
Room: Restaurant 1
Friday 13 May 2022
09:00 ML as a service, QML, reconstruction
ML as a service, QML, reconstruction
09:00 - 10:45
Room: 500/1-001 - Main Auditorium
Contributions

09:00 Neural network distributed training and optimization library (NNLO) - Irena Veljanovic (CERN)

09:25 MLaaS4HEP: Machine Learning as a Service for HEP - Luca Giommi (Universita e INFN, Bologna (IT))

09:30 Quantum Machine Learning algorithms in the latent space of HEP events - Kinga Anna Wozniak (University of Vienna (AT))

09:55 GNN-based algorithm for full-event filtering and interpretation at the LHCb trigger - Julian Garcia Pardinas (Universita & INFN, Milano-Bicocca (IT))

10:20 Graph Neural Network Track Reconstruction for the ATLAS ITk Detector - Daniel Thomas Murnane (Lawrence Berkeley National Lab. (US))
10:45 Coffee Break
Coffee Break
10:45 - 11:15
Room: 500/1-001 - Main Auditorium
11:15 Reconstruction and identification
Reconstruction and identification
11:15 - 12:30
Room: 500/1-001 - Main Auditorium
Contributions

11:15 Application of artificial intelligence in the reconstruction of signals from the PADME electromagnetic calorimeter - Kalina Stoimenova (Sofia University "St. Kliment Ohridski")

11:20 Semi-supervised Graph Neural Networks for Pileup Noise Removal - Garyfallia Paspalaki (Purdue University (US))

11:25 CBM performance for (multi-)strange hadron measurements using Machine Learning techniques - Shahid Khan

11:30 Leveraging universality of jet taggers through transfer learning - Radoslaw Piotr Grabarczyk

11:55 Particle Transformer for Jet Tagging - Sitian Qian (Peking University (CN))

12:20 ML for SUEP Detection - Luca Marco Lavezzo (MIT)

12:25 Using Graph autoencoders to trigger on new physics at the LHC - Muhammad-Hassan Shahid
12:30 Lunch Break
Lunch Break
12:30 - 14:00
Room: 500/1-001 - Main Auditorium
14:00 Identification, reconstruction, and experimental design
Identification, reconstruction, and experimental design
14:00 - 16:00
Room: 500/1-001 - Main Auditorium
Contributions

14:00 Likelihood-Free Frequentist Inference for Calorimetric Muon Energy Measurement - Luca Masserano (Carnegie Mellon University)

14:25 Two-level graphs for muon-tomography inference - Giles Chatham Strong (Universita e INFN, Padova (IT))

14:50 Electron identification in ATLAS using a deep neural network - Lukas Ehrke (Universite de Geneve (CH))

14:55 Tracking of Proton Traces in a Digital Tracking Calorimeter using Reinforcement Learning - Tobias Kortus (University of Applied Sciences Worms)

15:10 Point Cloud Deep Learning Methods for Pion Reconstruction in the ATLAS Detector - Mariel Pettee (Lawrence Berkeley National Lab. (US))

15:35 Explaining machine-learned particle-flow reconstruction - Farouk Mokhtar (Univ. of California San Diego (US))
16:00 Closing session
Closing session
16:00 - 16:30
Room: 500/1-001 - Main Auditorium
Contributions

16:00 Workshop closing - Andrea Wulzer (CERN and EPFL) Anja Butter David Rousseau (IJCLab-Orsay) Fabio Catalano (University and INFN Torino (IT)) Gian Michele Innocenti (CERN) Lorenzo Moneta (CERN) Michael Aaron Kagan (SLAC National Accelerator Laboratory (US)) Pietro Vischia (Universite Catholique de Louvain (UCL) (BE)) Riccardo Torre (CERN) Simon Akar (University of Cincinnati (US))

Choose timezone