8โ€“12 Sept 2025
Hamburg, Germany
Europe/Berlin timezone

Practical Neural Simulation-Based Inference at the LHC

11 Sept 2025, 12:30
30m
ESA A

ESA A

Plenary Track 2: Data Analysis - Algorithms and Tools Plenary

Speaker

Jay Ajitbhai Sandesara (University of Wisconsin Madison (US))

Description

Neural Simulation-Based Inference (NSBI) is an emerging class of statistical methods that harness the power of modern deep learning to perform inference directly from high-dimensional data. These techniques have already demonstrated significant sensitivity gains in precision measurements across several domains, outperforming traditional approaches that rely on low-dimensional summaries. This talk will focus on the practical application of NSBI in LHC analyses, highlighting recent progress and ongoing efforts in the field. We will explore the challenges of scaling NSBI workflows to complex, high-dimensional parameter spaces, and discuss strategies developed to address these issues. We will also present progress towards the development of a computationally efficient and practical NSBI analysis framework tailored for use in high-energy physics experiments.

Significance

The presentation will cover the development of a new end-to-end tool that can be widely used by LHC collaborations to perform NSBI measurements. It will also cover new techniques that enable scaling workflow to LHC measurements.

Experiment context, if any ATLAS, CMS

Authors

Alexander Held (University of Wisconsin Madison (US)) Jay Ajitbhai Sandesara (University of Wisconsin Madison (US)) Kyle Stuart Cranmer (University of Wisconsin Madison (US)) Massimiliano Galli (Princeton University (US)) Matthew Feickert (University of Wisconsin Madison (US)) Peter Elmer (Princeton University (US))

Presentation materials