Login

Simulation-Based Inference Blueprint

26–27 Feb 2026
CERN
Europe/Berlin timezone

An IRIS-HEP Blueprint Workshop

Contribution List

32 out of 32 displayed
Export to PDF
  1. 1. Welcome and Introduction
    Jay Ajitbhai Sandesara (University of Wisconsin Madison (US)), Nick Smith (Fermi National Accelerator Lab. (US))
    26/02/2026, 10:00
  2. 2. Simulation-Based Inference — An Introduction
    Gilles Louppe
    26/02/2026, 10:20
  3. 13. Discussion
    26/02/2026, 10:50
  4. 6. Simulation-Based Inference in ATLAS
    Tae Hyoun Park (Max Planck Society (DE))
    26/02/2026, 11:10
  5. 4. Simulation-Based Inference in CMS
    Sergio Sanchez Cruz (Universidad de Oviedo (ES))
    26/02/2026, 11:25
  6. 14. Discussion
    26/02/2026, 11:40
  7. 7. HistFactory Introduction
    Alexander Held (University of Wisconsin Madison (US))
    26/02/2026, 13:30
  8. 8. HistFactory v2: Systematics Modeling with Gaussian Processes
    Jay Ajitbhai Sandesara (University of Wisconsin Madison (US))
    26/02/2026, 13:50
  9. 15. Unbinned measurements with machine-learned systematic uncertainties
    Ricardo Barrué (Marietta Blau Institute for Particle Physics)
    26/02/2026, 14:10
  10. 9. Discussion
    26/02/2026, 14:30
  11. 10. Direct Likelihood Learning and Uncertainty Profiling with Normalizing Flows
    Davide Valsecchi (ETH Zurich (CH))
    26/02/2026, 15:30

    Recent advances in Simulation-Based Inference (SBI) often rely on training classifiers to approximate likelihood ratios. However, direct density estimation using Normalizing Flows offers distinct advantages, particularly in the flexibility of the learned statistical model. In this presentation, we explore the use of Normalizing Flows to learn the likelihood function directly to infer physics...

    Go to contribution page
  12. 11. Neural (Quasi-)Probabilistic Likelihood Ratio Estimation
    Matthew Drnevich (New York University (US)), Stephen Jiggins (Deutsches Elektronen-Synchrotron (DE))
    26/02/2026, 15:50
  13. 12. Discussion
    26/02/2026, 16:10
  14. 24. Toolkit for Simulation-Based Inference (IRIS-HEP)
    Jay Ajitbhai Sandesara (University of Wisconsin Madison (US))
    27/02/2026, 10:00
  15. 25. Q&A
    27/02/2026, 10:30
  16. 21. NEEDLE: Workflow Orchestration for Large-Scale NSBI Deployment
    Kylian Schmidt (KIT - Karlsruhe Institute of Technology (DE)), Levi Evans (Deutsches Elektronen-Synchrotron (DE))
    27/02/2026, 10:40

    Neural Simulation Based Inference is a fast-moving field with many ongoing efforts to share these promising methods with the wider HEP community. Whilst the specific NSBI methods that will eventually find adoption in actual analyses are not yet known, it is clear that most approaches face a set of common challenges. Foremost, the reliance on many large neural networks that train on large...

    Go to contribution page
  17. 26. Q&A
    27/02/2026, 11:05
  18. 27. SBI Toolkit Modification and robust Uncertainty Quantification
    Jingjing Pan (KIT - Karlsruhe Institute of Technology (DE))
    27/02/2026, 11:15

    We are exploring the application of the IRIS-HEP Simulation-Based Inference (SBI) toolkit to precision Higgs measurements. In this talk, we discuss methodological developments aimed at improving robustness and of SBI workflows in realistic LHC settings.

    On the tooling side, we explore physics-informed inductive biases in neural architectures, energy-conserving optimization schemes as...

    Go to contribution page
  19. 32. Broader Discussion
    27/02/2026, 11:35
  20. 28. Building summaries with event2vec
    Nick Smith (Fermi National Accelerator Lab. (US)), Prasanth Shyamsundar (Fermi National Accelerator Laboratory)
    27/02/2026, 13:30

    In this work, we introduce some machine learning techniques for training sensitive vector-representations or vector-summaries of collider events. The vector-summaries of the individual events in a dataset can be directly summed up and analyzed further. For EFT searches, our approach leads to a powerful and convenient middle ground between traditional histogram-based analyses and SBI analyses...

    Go to contribution page
  21. 29. Parametrized Optimal Observable Approach to NSBI
    Matthew Kenneth Maroun (University of Massachusetts (US))
    27/02/2026, 13:50

    The parametrized optimal observable approach is a binned approximation to the full NSBI formalism introduced in [Rep. Prog. Phys. 88 (2025) 067801]. We present the method highlighting it's advantages and limitations. We will show a practical implementation of the parametrized optional observable formalism in RooFit and show how it can be used to construct Asimov datasets and to perform Neyman...

    Go to contribution page
  22. 22. Tooling issues for binned nSBI analyses with pyhf and how to overcome them
    Malin Elisabeth Horstmann (Technische Universitat Munchen (DE))
    27/02/2026, 14:10

    Neural estimates of likelihood ratios provide a powerful approach to extending sensitivity across wide regions of phase space, but their integration into full HEP analyses presents significant technical challenges. The computational cost of unbinned neural simulation-based inference (nSBI) can be reduced by performing binned fits using optimal observables - whilst still retaining the benefits...

    Go to contribution page
  23. 30. Discussion
    27/02/2026, 14:30
  24. 23. Scaling Neural Simulation-Based Inference at High Performance Computing for LHC analysis
    Walter Hopkins (Argonne National Laboratory (US)), Xiangyang Ju (Lawrence Berkeley National Lab. (US))
    27/02/2026, 15:30

    This talk will present the preliminary work on scaling the Machine Learning training and Hyperparameter optimization (HPO) at High Performance Computers. We leveraged the Pytorch Lightning framework for distributed training and Ray Tune for HPO. In addition, the ML training framework automatically monitors the model’s physics performance by evaluating Neural Simulation Based Inference (NSBI)...

    Go to contribution page
  25. 16. SBI for Effective Field Theories
    Nick Smith (Fermi National Accelerator Lab. (US))
    27/02/2026, 16:00
  26. 31. Closeout
    Jay Ajitbhai Sandesara (University of Wisconsin Madison (US)), Nick Smith (Fermi National Accelerator Lab. (US))
    27/02/2026, 16:30
  27. 17. Case Review - pyhf toolkit
    Matthew Feickert (University of Wisconsin Madison (US))
  28. 19. Coffee break
  29. 20. Coffee break
  30. 3. Neural Networks for Density (Ratio) Estimation
  31. 18. SBI case for Effective Field Theories
    Nick Smith (Fermi National Accelerator Lab. (US))
  32. 5. VHbb analysis with fixed likelihood ratio - CMS