24–28 Aug 2026
Kirchhoff Institute for Physics (KIP)
Europe/Berlin timezone

Generative and geometric learning for comprehensive collider event reconstruction

25 Aug 2026, 11:50
8m
3.404

3.404

Patterns & Anomalies 🔀 Patterns & Anomalies

Speaker

Ethan Simpson (The University of Manchester (GB))

Description

In particle collider experiments, event reconstruction is the task of inferring the kinematics of the short-lived, 'interesting' particles of the hard scatter from the stable final states recorded by detectors. We decompose event reconstruction into two tasks: assigning measured jets and leptons to parent particles, and regressing unmeasured neutrino kinematics. We present a novel geometric learning framework that represents collider events as hypergraphs, achieving state-of-the-art performance in the assignment task. The hypergraph model is interfaced with a generative diffusion model to infer inherently multimodal neutrino kinematics distributions. We showcase the approach in several proton-proton collision processes, demonstrating new avenues for analysis in Higgs, electroweak boson and top-quark physics.

Author

Ethan Simpson (The University of Manchester (GB))

Presentation materials