19–23 May 2025
CERN
Europe/Zurich timezone

On focusing statistical power for searches and measurements in particle physics

Not scheduled
20m
61/1-201 - Pas perdus - Not a meeting room - (CERN)

61/1-201 - Pas perdus - Not a meeting room -

CERN

10
Show room on map
Poster 2 ML for analysis: Event classification, statistical analysis and inference, anomaly detection Poster Session

Speaker

James Carzon (Carnegie Mellon University)

Description

Particle physics experiments rely on the (generalised) likelihood ratio test (LRT) for searches and measurements. This is not guaranteed to be optimal for composite hypothesis tests, as the Neyman-Pearson lemma pertains only to simple hypothesis tests. An improvement in the core statistical testing methodology would have widespread ramifications across experiments. We discuss an alternate test statistic that provides the data analiser an ability to focus the power of the test in physics-motivated regions of the parameter space. We demonstrate the improvement from this technique compared to the LRT on the Higgs -> tau tau HiggsML dataset simulated by the ATLAS experiment and a dark matter (WIMPs) dataset inspired by the LZ experiment. This technique can be coupled with neural simulation-based inference techniques to best leverage information available in complex particle physics data. This technique also employs machine learning to efficiently perform the Neyman construction that is essential to ensure valid confidence intervals.

Would you like to be considered for an oral presentation? Yes

Author

James Carzon (Carnegie Mellon University)

Co-authors

Aishik Ghosh (University of California Irvine (US)) Ann Lee (Carnegie Mellon University) Daniel Whiteson (University of California Irvine (US)) Luca Masserano (Carnegie Mellon University) Rafael Izbicki (Federal University of Sao Carlos)

Presentation materials

There are no materials yet.