24–26 May 2021
University of Pittsburgh
US/Eastern timezone

Searching for soft leptons in compressed spectra with a Boosted Decision Tree

25 May 2021, 18:00
15m
BSM BSM IV

Speakers

Alyssa Horne (Sam Houston State Univeristy)Mr Marcus Snedeker (Sam Houston State University)

Description

Collider searches for electroweak final states from decays involving narrow mass gaps in a new physics sector are kinematically limited by softness of the scattering products. In a prior study, we required a hard initial state jet in order to boost the visible system, and exploited variations in angular separations to suppress topologically identical backgrounds from WW+jets. Presently, we revisit that analysis to establish how much improvement may be realized by the application of machine learning techniques. We provide a boosted decision tree (BDT) with a combination of high-level (e.g. ditau invariant mass, MT2, cos-theta-star), and low-level (e.g. angular separations, PT ratios) variables. We find that the BDT functions most efficiently if “obvious” event selections (e.g. MET, dilepton Z-window) are applied at the outset, and if individual trainings against similar backgrounds are merged into a composite classification score. This approach yields significantly stronger background suppression and signal retention than could be achieved with manual optimization of cuts.

Primary authors

Alyssa Horne (Sam Houston State Univeristy) Mr Marcus Snedeker (Sam Houston State University)

Co-authors

Bhaskar Dutta (Texas A&M University) Jason Kumar (University of Hawaii) Joel Walker (Sam Houston State University) Dr Patrick Stengel (Stockholm University) Pearl Sandick (University of Utah) Tathagata Ghosh (University of Hawaii at Manoa)

Presentation materials