Name: 7th Inter-Experimental LHC Machine Learning Workshop
Start: 2025-05-19T09:00:00+02:00
End: 2025-05-23T12:40:00+02:00
Location: CERN

7th Inter-Experimental LHC Machine Learning Workshop

from Monday, 19 May 2025 (09:00) to Friday, 23 May 2025 (12:40)

Monday, 19 May 2025

09:00 Other: Fair Universe HiggsML Uncertainty CERN workshop [https://indico.cern.ch/event/1523250/]
Fair Universe HiggsML Uncertainty CERN workshop [https://indico.cern.ch/event/1523250/]
09:00 - 13:00
Room: 222/R-001
14:00 Welcome - Matthias Komm (Deutsches Elektronen-Synchrotron (DE))
Welcome
- Matthias Komm (Deutsches Elektronen-Synchrotron (DE))
14:00 - 14:05
Room: 222/R-001
14:05 Keynotes ML Research
14:05 - 16:05
Room: 222/R-001
Contributions

14:05 Weather forecasting with foundational models - Ilaria Luise (ECMWF)

15:05 Neural differential equations - Patrick Kidger (Cradle.bio)
16:05 Coffee
Coffee
16:05 - 16:30
Room: 222/R-001
16:30 Keynotes Physics + ML
16:30 - 17:20
Room: 222/R-001
Contributions

16:30 Neural Simulation-Based Inference for HEP - Aishik Ghosh (University of California Irvine (US))
Tuesday, 20 May 2025
09:00 Keynotes Physics + ML
09:00 - 10:00
Room: 222/R-001
Contributions

09:00 AI & HPC - Eric Wulff (CERN)
10:00 Coffee
Coffee
10:00 - 10:30
Room: 222/R-001
10:30 Contributed Talks
10:30 - 12:30
Room: 222/R-001
Contributions

10:30 Cross-Geometry Fast Electromagnetic Shower Simulation - Lorenzo Valente (University of Hamburg)

10:50 CMS FlashSim: how an end-to-end ML approach speeds up simulation in CMS - Francesco Vaselli (Scuola Normale Superiore & INFN Pisa (IT))

11:10 End-to-End Optimal Detector Design with Mutual Information Surrogates - Stephen Mulligan (Universite de Geneve (CH))

11:30 DDFastShowerML: A Library for ML-based Fast Calorimeter Shower Simulation at Future Collider Experiments and Beyond - Peter McKeown (CERN)

11:50 Why so Negative? Neural Quasiprobabilistic Likelihood Ratio Estimation with Negatively Weighted Data - Matthew Drnevich (New York University (US))
12:30 Lunch
Lunch
12:30 - 14:00
Room: 222/R-001
14:00 Contributed Talks
14:00 - 15:30
Room: 222/R-001
Contributions

14:00 Optimisation of the Accelerator Control by Reinforcement Learning: A Simulation-Based Approach - Anwar Ibrahim

14:20 Physics Instrument Design with Reinforcement Learning - Shah Rukh Qasim (University of Zurich (CH))

14:40 Convolutional pile-up suppression in the ATLAS Global Trigger - Noah Clarke Hall (University College London)
15:30 Coffee
Coffee
15:30 - 16:00
Room: 222/R-001

16:00 Poster Session

16:00 - 17:30
Room: 61/1-201 - Pas perdus - Not a meeting room -

17:30 Welcome Drink
Welcome Drink
17:30 - 19:00
Room: 61/1-201 - Pas perdus - Not a meeting room -
Wednesday, 21 May 2025
09:00 EuCAIF joint session: FAIR and sustainable machine learning
09:00 - 10:30
Room: 222/R-001
Contributions

09:00 Session program: see EuCAIF indico on https://indico.cern.ch/e/EuCAIF-FAIR-Sustainable-kickoff.
10:30 Coffee
Coffee
10:30 - 11:00
Room: 222/R-001
11:00 Other: CERN Data Science seminar
CERN Data Science seminar
11:00 - 12:00
Room: 222/R-001
Contributions

11:00 Robotics & Reinforcement Learning - Antonin Raffin (German Aerospace Center (DLR))
12:00 Lunch
Lunch
12:00 - 14:00
Room: 222/R-001
14:00 Contributed Talks
14:00 - 16:00
Room: 222/R-001
Contributions

14:00 Anomaly Detection techniques applied to the Quality Control of new detector components - Louis Vaslin (KEK High Energy Accelerator Research Organization (JP))

14:20 Latest improvements to CATHODE - Chitrakshee Yede (Hamburg University (DE))

14:40 Weakly supervised signal detection for RPV SUSY multijet inclusive search - Takane Sano (Kyoto University (JP))

15:00 Supervised contrastive learning for streamlined analysis & anomaly detection - Samuel Kai Bright-Thonney (Massachusetts Inst. of Technology (US))

15:20 Contrastive Normalizing Flows for Uncertainty-Aware Parameter Estimation - Ibrahim Elsharkawy (University of Illinois Urbana-Champaign)

15:40 Anomaly preserving contrastive neural embeddings for end-to-end model-independent searches at the LHC - Kyle Sidney Metzger
16:00 Coffee
Coffee
16:00 - 16:30
Room: 222/R-001
16:30 Contributed Talks
16:30 - 18:00
Room: 222/R-001
Contributions

16:30 Integrating Energy Flow Networks with Jet Substructure Observables for Enhanced Jet Quenching Studies - João A. Gonçalves (LIP - IST)

16:50 Automatizing the search for mass resonances using BumpNet - Ethan James Meszaros (Université de Montréal (CA))

17:10 Reinforcement Learning for background determination in particle physics - Guillermo Hijano Mendizabal (University of Zurich (CH))

17:30 Evaluating Two-Sample Tests for Validating Generators in Precision Sciences - Samuele Grossi (Università degli studi di Genova & INFN sezione di Genova)
Thursday, 22 May 2025
09:00 Tutorials
09:00 - 10:30
Room: 222/R-001
Contributions

09:00 MLOps infrastructure & best practices - Ricardo Rocha (CERN)
10:30 Coffee
Coffee
10:30 - 11:00
Room: 222/R-001
11:00 Tutorials
11:00 - 12:30
Room: 222/R-001
Contributions

11:00 Tensor Networks - Enrique Rico Ortega (CERN)
12:30 Lunch
Lunch
12:30 - 14:00
Room: 222/R-001
14:00 Contributed Talks
14:00 - 15:30
Room: 222/R-001
Contributions

14:00 DINAMO: Dynamic and INterpretable Anomaly MOnitoring for Large-Scale Particle Physics Experiments - Arsenii Gavrikov

14:20 Autoencoder-based time series anomaly detection for ATLAS Liquid Argon calorimeter data quality monitoring - Vilius Čepaitis (Université de Genève (CH))

14:40 Challenges Deploying a Hybrid PVFinder Algorithm for Primary Vertex Reconstruction in LHCb’s GPU-Resident HLT1 - Mohamed Elashri (University of Cincinnati)
15:30 Coffee
Coffee
15:30 - 16:00
Room: 222/R-001

16:00 Poster Session

16:00 - 18:00
Room: 61/1-201 - Pas perdus - Not a meeting room -

18:00 SMARTHEP Meets Industry @CERN https://indico.cern.ch/event/1518429/contributions/6431628/
SMARTHEP Meets Industry @CERN https://indico.cern.ch/event/1518429/contributions/6431628/
18:00 - 19:30
Room: 500/1-001 - Main Auditorium https://indico.cern.ch/event/1518429/contributions/6431628/

19:30 Apero with the SMARTHEP network and Confindustria Piedmont
Apero with the SMARTHEP network and Confindustria Piedmont
19:30 - 20:30
Room: 61/1-201 - Pas perdus - Not a meeting room -
Friday, 23 May 2025
09:00 Keynotes Physics + ML: CALO Challenge
CALO Challenge
09:00 - 10:00
Room: 222/R-001
Contributions

09:00 Summary of Calo Challenge - Claudius Krause (HEPHY Vienna (ÖAW))
10:00 Coffee
Coffee
10:00 - 10:30
Room: 222/R-001
10:30 Contributed Talks
10:30 - 12:00
Room: 222/R-001
Contributions

10:30 Robust Model Selection for Deep Learning - Alexey Boldyrev

10:50 Automated Model Building with Reinforcement Learning: An Application to Neutrino Model Building - Jake Rudolph

11:10 Scalable Multi-Task Learning for Event Reconstruction with Heterogeneous Graph Neural Networks - William Sutcliffe (University of Zurich (CH))

11:30 PQuant: A Tool for End-to-End Hardware-Aware Model Compression - Roope Oskari Niemi
12:00 Best poster lightning talk
Best poster lightning talk
12:00 - 12:05
Room: 222/R-001
12:05 Summary - Michał Mazurek (National Centre for Nuclear Research (PL))
Summary
- Michał Mazurek (National Centre for Nuclear Research (PL))
12:05 - 12:35
Room: 222/R-001