14–18 Sept 2026
Europe/Vienna timezone

Domain Adaptation in Colliders: Reconcile Simulation and Data

14 Sept 2026, 16:20
20m

Speaker

Shang-Fu Wei (The University of Tokyo)

Description

Multivariate classifiers in collider physics increasingly use low-level detector information to maximize sensitivity, but this often amplifies systematic uncertainties arising from mismodelling in simulation. To address this, we apply unsupervised domain adaptation (UDA), allowing the classifier to learn with both simulated and unlabeled real data during training, thereby reducing sensitivity to simulation-induced domain shifts. Our approach leverages a maximum mean discrepancy (MMD) penalty as a plug-in module for standard deep learning architectures. Using a case study of VBF versus ggF Higgs classification in H→γγ with both CNN and Particle Transformer architectures, we show that this method consistently improves classifier robustness and reduces cross section measurement uncertainty, demonstrating its universal effectiveness across data types.

Authors

Dr Alexander Karlberg (CERN) Prof. Cheng-Wei Chiang (National Taiwan University) David Shih Shang-Fu Wei (The University of Tokyo) Stephane Brunet Cooperstein (Univ. of California San Diego (US))

Presentation materials

There are no materials yet.