Abstract
The ABCD method is one of the most widely used data-driven background estimation techniques in high energy physics. Cuts on two statistically-independent classifiers separate signal and background into four regions, so that background in the signal region can be estimated simply using the other three control regions. Typically, the independent classifiers are chosen "by hand" to be intuitive and physically motivated variables. Here, we explore the possibility of automating the design of one or both of these classifiers using machine learning. We show how to use state-of-the-art decorrelation methods to construct powerful yet independent discriminators. Along the way, we uncover a previously unappreciated aspect of the ABCD method: its accuracy hinges on having low signal contamination in control regions not just overall, but relative to the signal fraction in the signal region. We demonstrate the method with three examples: a simple model consisting of three-dimensional Gaussians; boosted hadronic top jet tagging; and a recasted search for paired dijet resonances. In all cases, automating the ABCD method with machine learning significantly improves performance in terms of ABCD closure, background rejection and signal contamination.
Highlights
A key component of high energy physics data analysis, whether for Standard Model (SM) measurements or searches beyond the SM, is background estimation
The idea behind all data-driven background estimation strategies is to extrapolate or interpolate from some control regions which are background dominated into a signal region of interest
We will show that single and double distance correlation (DisCo) improve the discrimination power and background closure of the ABCD method but can significantly reduce the level of signal contamination at the same time
Summary
A key component of high energy physics data analysis, whether for Standard Model (SM) measurements or searches beyond the SM, is background estimation. The idea of the ABCD method is to pick two observables f and g (for example, the invariant mass of a dijet system and the rapidity of that system) which are approximately statistically independent for the background, and which are effective discriminators of signal versus background. Simple thresholds on these observables partition events into four regions. This simulation correction has small uncertainties—either because the effect itself is small, or because the correction is robust Such corrections, together with the fact that simple kinematic features are typically not optimal discriminants of signal versus background, generally limit the effectiveness of the ABCD method and the sensitivity of the analysis in question.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
